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. 3849
    Prev
    Next
    INDEX
    Explanations

    sequences of dollar signs typically used in programming to indicate variables

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

    Characters preceding code or variables

    np_acts-logits-general · gemini-2.0-flash

    programmatic context and scientific data

    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
     auto
    -0.62
    elaar
    -0.58
    hahn
    -0.56
    äinen
    -0.56
     Day
    -0.55
     Schwe
    -0.54
    IRUS
    -0.54
    letten
    -0.54
     If
    -0.53
    ernas
    -0.53
    POSITIVE LOGITS
    GLOBALS
    0.85
    this
    0.78
    enumi
    0.72
    EndContext
    0.69
     Процитовано
    0.66
    ="{{$
    0.63
    principalColumn
    0.63
     المعيارى
    0.62
     ModelExpression
    0.62
    \{\\
    0.62
    Activations Density 0.038%

    No Known Activations