© 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. 27701
    Prev
    Next
    INDEX
    Explanations

    proper nouns and scientific terminologies related to biology and materials

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

    Prefixes of names and scientific terms

    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
    AccessorTable
    -0.84
    oporosis
    -0.83
     Mulder
    -0.82
     Woodward
    -0.78
    jabi
    -0.76
    间
    -0.73
     augus
    -0.73
    tagext
    -0.72
    wickshire
    -0.72
    bunal
    -0.71
    POSITIVE LOGITS
    flink
    0.82
     Oli
    0.79
    ChildScrollView
    0.77
     kaynağından
    0.77
     Ciri
    0.75
    ly
    0.73
    склю
    0.71
     Ezek
    0.70
    ToBounds
    0.70
     Gründ
    0.70
    Activations Density 0.729%

    No Known Activations