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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14963
    Prev
    Next
    INDEX
    Explanations

    situations involving offers and agreements

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

    Agreement or acceptance

    np_acts-logits-general · gemini-2.0-flash

    accept or agree

    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
    detectChanges
    -0.52
    memoized
    -0.52
    SerializedSize
    -0.51
    fillType
    -0.49
    WithIOException
    -0.49
    Abitanti
    -0.48
    flashdata
    -0.47
    ranean
    -0.45
    افظ
    -0.45
     Forecast
    -0.45
    POSITIVE LOGITS
     accepted
    1.91
     accepting
    1.79
     accept
    1.75
     Accepting
    1.70
     accepts
    1.68
     acceptance
    1.68
    accepted
    1.63
     Accepted
    1.63
    accept
    1.61
    Accepted
    1.61
    Activations Density 0.326%

    No Known Activations