Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2
    Prev
    Next
    INDEX
    Explanations

    phrases related to recorded information or evidence, particularly in the context of interviews, interrogations, or audio/video recordings.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @jbloomaus

    elements related to interviews and interrogation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    audio or video recordings

    np_acts-logits-general · gemini-2.0-flash

    audio and video recording

    np_acts-logits-general · gemini-2.5-flash-lite

    Passive voice constructions with auxiliary verbs (particularly "was" and "were") paired with past participles or present participles, often describing actions involving recording, documentation, or evidence in formal or legal contexts.

    eleuther_acts_top20 · claude-4-5-haikuTriggered by @inbal42
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.81
     autorytatywna
    -0.79
     שוליים
    -0.66
     vectorielle
    -0.65
     vectorielles
    -0.64
    RegistryLite
    -0.62
     viewDidLoad
    -0.62
     resourceCulture
    -0.61
     renseignements
    -0.61
     vettoriale
    -0.61
    POSITIVE LOGITS
     recording
    1.79
     recordings
    1.75
     recorded
    1.63
    recording
    1.49
     tape
    1.46
     Recording
    1.44
     tapes
    1.44
    recorded
    1.39
     recorder
    1.38
     Recordings
    1.38
    Activations Density 0.352%

    No Known Activations