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. 130974
    Prev
    Next
    INDEX
    Explanations

    specifications related to formatting dimensions in a document

    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
    :+:
    -0.36
     llaman
    -0.35
     sogno
    -0.35
     Nere
    -0.34
    get
    -0.34
    rna
    -0.32
     sire
    -0.32
     get
    -0.31
     recuer
    -0.31
    pun
    -0.30
    POSITIVE LOGITS
    textwidth
    0.96
    sidemargin
    0.93
     EconPapers
    0.83
    InputBorder
    0.79
    ChildScrollView
    0.79
    randomUUID
    0.70
    Personendaten
    0.69
    enderror
    0.69
    Espèce
    0.69
     typelib
    0.68
    Activations Density 0.006%

    No Known Activations