Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 93533
    Prev
    Next
    INDEX
    Explanations

    mentions of posts and comments in a discussion context

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

    blog posts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     QtCore
    -0.47
    AddTagHelper
    -0.45
    EndInit
    -0.37
     '\\;'
    -0.36
    الإنجليزية
    -0.36
    strconv
    -0.36
    sizeCache
    -0.34
    LayoutStyle
    -0.32
    <tbody>
    -0.31
     SqlDbType
    -0.30
    POSITIVE LOGITS
    posts
    0.68
     post
    0.67
     posts
    0.65
    post
    0.65
     posting
    0.64
     الرياضيه
    0.62
     posted
    0.60
     getPost
    0.60
     announcing
    0.60
    posting
    0.57
    Activations Density 0.014%

    No Known Activations