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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 24530
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ownership and connection between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     Othello
    -0.35
     simply
    -0.34
     definitely
    -0.32
     generally
    -0.31
     that
    -0.31
     my
    -0.29
     this
    -0.29
    之所以
    -0.28
     obviously
    -0.27
     or
    -0.27
    POSITIVE LOGITS
     MainAxisSize
    1.03
    sizeCache
    0.89
    MigrationBuilder
    0.86
    writeFieldEnd
    0.81
    脚注の使い方
    0.80
    VersionUID
    0.79
     defaultstate
    0.78
     مشين
    0.77
    rungsseite
    0.76
     propOrder
    0.76
    Activations Density 0.011%

    No Known Activations