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. 16357
    Prev
    Next
    INDEX
    Explanations

    specific formatting and structure elements in web addresses or information related to URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    A beginning-of-sequence marker that precedes the start of a new document or text segment, typically followed by a title or header text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    IndentedString
    -0.56
    featureID
    -0.50
    inerea
    -0.45
    delwed
    -0.44
    cord
    -0.44
    ContentLoaded
    -0.43
     Deel
    -0.43
     Stretch
    -0.43
    cura
    -0.42
    imple
    -0.42
    POSITIVE LOGITS
     noqa
    0.56
     localObject
    0.52
    RTEE
    0.45
    Aiheesta
    0.42
     paramInt
    0.41
    xase
    0.41
     uLocal
    0.41
    awtextra
    0.40
    ValueStyle
    0.39
     Мексичка
    0.39
    Activations Density 0.058%

    No Known Activations