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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5329
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords associated with programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coroa
    -0.34
     antemano
    -0.31
    rección
    -0.31
     hierbas
    -0.30
     externi
    -0.30
     seleção
    -0.30
    minyak
    -0.29
     artikkelen
    -0.29
     bruja
    -0.29
     außerhalb
    -0.28
    POSITIVE LOGITS
    GEBURTSDATUM
    0.65
    windowFixed
    0.64
    WebpackPlugin
    0.59
    AndEndTag
    0.58
    aarrggbb
    0.58
    complexType
    0.57
    styleType
    0.55
     Biôgrafia
    0.55
     endwhile
    0.54
    writeFieldEnd
    0.54
    Activations Density 1.718%

    No Known Activations