© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2650
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal frameworks and organizational processes

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

    followed by an infinitive verb

    np_acts-logits-general · gemini-2.0-flash

    verbs of action following "to"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     specialises
    -0.82
     Favourite
    -0.79
     scepticism
    -0.77
     apologised
    -0.77
    Whilst
    -0.77
     Initialise
    -0.77
    Favourite
    -0.76
     realising
    -0.74
    organisation
    -0.74
     apologise
    -0.73
    POSITIVE LOGITS
     utilize
    0.67
     utilized
    0.59
     utilizing
    0.57
     favorably
    0.56
     develop
    0.54
     identify
    0.54
     utilizes
    0.52
     identified
    0.51
     implement
    0.51
     aggressively
    0.51
    Activations Density 0.682%

    No Known Activations