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. 53749
    Prev
    Next
    INDEX
    Explanations

    queries and questions related to code submission and review processes

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

    Instructions and polite directives in online communities, often using second-person pronouns and phrases like "please" that guide user behavior or request specific actions.

    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
     group
    -0.38
     internal
    -0.38
     Northern
    -0.35
     Home
    -0.35
     extension
    -0.35
     Old
    -0.35
     Beginning
    -0.34
     Eber
    -0.34
     two
    -0.34
     home
    -0.34
    POSITIVE LOGITS
    twimg
    0.65
     desmotivaciones
    0.57
    utilisons
    0.55
    findpost
    0.54
     pinulongan
    0.54
    ScopeManager
    0.54
     kasarigan
    0.53
    haikusbot
    0.53
     pouvoit
    0.52
     ainfi
    0.52
    Activations Density 0.063%

    No Known Activations