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. 24-GEMMASCOPE-RES-131K
    6. 1069
    Prev
    Next
    INDEX
    Explanations

    patterns in numerical values and code structure

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

    programming comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndProject
    -0.68
    posedge
    -0.65
    parsedMessage
    -0.65
    ariConfig
    -0.55
    AccessFile
    -0.53
     terciopelo
    -0.53
     vooz
    -0.53
     ERSITY
    -0.52
     RIPRODUZIONE
    -0.52
    IsMutable
    -0.52
    POSITIVE LOGITS
    一
    0.43
    Happy
    0.40
    ↵
    0.39
    ↵↵
    0.39
     Happy
    0.38
    ">//
    0.37
     Cleaner
    0.37
    EN
    0.37
    2
    0.37
    migrationBuilder
    0.36
    Activations Density 0.001%

    No Known Activations