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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 15714
    Prev
    Next
    INDEX
    Explanations

    references to statistical analysis or methodology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.61
    <eos>
    -0.52
     Anna
    -0.49
    #
    -0.48
    ↵↵
    -0.48
    C
    -0.47
                                   
    -0.47
    j
    -0.47
    ...
    -0.46
     (
    -0.46
    POSITIVE LOGITS
    Datuak
    1.42
    tagHelperRunner
    1.16
    NUMX
    1.13
    MigrationBuilder
    1.09
     समीक्षाओं
    1.05
    Personensuche
    1.04
    ftagPool
    0.99
     ExecuteAsync
    0.98
     autorytatywna
    0.98
    writeFieldEnd
    0.97
    Activations Density 0.021%

    No Known Activations