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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 7962
    Prev
    Next
    INDEX
    Explanations

    phrases related to clinical observations, durations, and processes

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

    length or duration

    np_acts-logits-general · gemini-2.0-flash

    duration and length

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umask
    -0.55
    spół
    -0.53
    нан
    -0.49
    baix
    -0.49
    onAttach
    -0.49
     htons
    -0.48
     CreateTagHelper
    -0.48
    bildet
    -0.48
    ^(@)
    -0.48
    gros
    -0.47
    POSITIVE LOGITS
     longer
    2.28
     longest
    2.25
     length
    2.13
     duration
    2.09
     Longer
    2.08
     lengthen
    2.08
     lengthened
    2.08
    Longer
    2.05
    longer
    2.02
     prolonged
    1.94
    Activations Density 0.841%

    No Known Activations