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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105148
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions involving sums, products, and numbers

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     autorytatywna
    -0.59
    principalColumn
    -0.55
    TypedDataSet
    -0.52
    
    -0.50
    fromnode
    -0.49
    توض
    -0.47
    onAttach
    -0.46
    ValueStyle
    -0.45
    EndGlobalSection
    -0.44
    tonode
    -0.43
    POSITIVE LOGITS
    رشف
    0.48
    ModelSerializer
    0.42
    клопе
    0.39
    setVerticalGroup
    0.39
     balancing
    0.37
    InputBorder
    0.36
     Савезне
    0.36
    zzleHttp
    0.35
     AssertionError
    0.35
    rceil
    0.34
    Activations Density 0.254%

    No Known Activations