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

    Neuronpedia

    APICircuit 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. 12-GEMMASCOPE-RES-16K
    6. 3011
    Prev
    Next
    INDEX
    Explanations

    references to authors and their contributions in academic or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sauvages
    -0.46
    .
    -0.42
     the
    -0.42
     sait
    -0.42
     passo
    -0.41
    rechter
    -0.41
     Públicas
    -0.41
     számára
    -0.41
    Ab
    -0.39
     scolaires
    -0.39
    POSITIVE LOGITS
    dafx
    1.12
     autorytatywna
    0.97
     surla
    0.91
    ///</
    0.84
    ViewImports
    0.83
     Wikimedijinoj
    0.81
    etheless
    0.81
    CodedInputStream
    0.81
    zzleHttp
    0.80
    ParallelGroup
    0.79
    Activations Density 0.351%

    No Known Activations