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. 122815
    Prev
    Next
    INDEX
    Explanations

    references to significant historical publications and authors

    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
    IntoConstraints
    -0.58
    $_['
    -0.54
    Autoritní
    -0.54
    InitStruct
    -0.51
    MigrationBuilder
    -0.45
    adone
    -0.43
     Etiquette
    -0.42
     Obligation
    -0.42
     reciproc
    -0.42
     Greed
    -0.41
    POSITIVE LOGITS
    脚注の使い方
    0.78
     published
    0.56
    iastes
    0.55
     publication
    0.55
     book
    0.53
     treatise
    0.52
    这本书
    0.48
    published
    0.46
     Italijanski
    0.45
    ouvrage
    0.45
    Activations Density 0.036%

    No Known Activations