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. 13-GEMMASCOPE-RES-16K
    6. 14686
    Prev
    Next
    INDEX
    Explanations

    a collection of alphanumeric codes or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pouvaient
    -0.45
     dormitorios
    -0.45
    дә
    -0.44
    Drift
    -0.43
    ย์
    -0.42
     Drift
    -0.42
    pros
    -0.40
    isesti
    -0.40
    備考
    -0.40
     sumpay
    -0.39
    POSITIVE LOGITS
    ThroughAttribute
    1.06
    GraphicsUnit
    1.03
     initComponents
    0.97
    脚注の使い方
    0.88
    MessageOf
    0.86
    CodedInputStream
    0.84
     ***!
    0.80
     propOrder
    0.80
    XmlAccessType
    0.77
    ConstraintMaker
    0.77
    Activations Density 1.327%

    No Known Activations