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. 33-GEMMASCOPE-RES-131K
    6. 65948
    Prev
    Next
    INDEX
    Explanations

    punctuations, specifically periods

    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_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.56
     ब्रेकडाउन
    -0.55
    évaluateur
    -0.49
    argout
    -0.49
     /*#__
    -0.47
     linkovi
    -0.46
     ModelExpression
    -0.46
     незавершена
    -0.43
     يتيمه
    -0.43
    apimachinery
    -0.43
    POSITIVE LOGITS
     ↑
    0.68
    tagHelperRunner
    0.46
     ^
    0.43
    :✨
    0.40
     agradec
    0.39
    NewUrlParser
    0.37
     leaping
    0.37
    ngiliz
    0.36
    postmedia
    0.36
     fallecido
    0.36
    Activations Density 0.001%

    No Known Activations