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. 17-GEMMASCOPE-RES-16K
    6. 9137
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical data related to populations or samples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.78
    ніципа
    -0.61
    CloseOperation
    -0.61
    zzlement
    -0.59
     AppComponent
    -0.59
    ppur
    -0.57
    isdir
    -0.55
    Diwedd
    -0.55
     anúncios
    -0.54
    hyrchwyd
    -0.53
    POSITIVE LOGITS
     percentile
    0.53
     perc
    0.50
    forChild
    0.49
    latego
    0.45
    بوابة
    0.45
    centiles
    0.45
     vanguardia
    0.43
     satélite
    0.43
    clusão
    0.42
    Perc
    0.42
    Activations Density 0.502%

    No Known Activations