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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28261
    Prev
    Next
    INDEX
    Explanations

    statements of possibility or conditionality regarding information validity

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

    may differ or cause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    beli
    -0.38
    ?
    -0.37
     &
    -0.37
    ავ
    -0.37
    Itoa
    -0.36
    bindParam
    -0.36
     št
    -0.36
    {
    -0.36
    Eloquent
    -0.36
     Warming
    -0.36
    POSITIVE LOGITS
    躇
    0.84
     propOrder
    0.78
    .")]
    0.71
    ]")]
    0.71
    antity
    0.70
     nahilalakip
    0.69
     مرئيه
    0.68
     subject
    0.68
     suaminya
    0.67
     delays
    0.66
    Activations Density 0.066%

    No Known Activations