© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105826
    Prev
    Next
    INDEX
    Explanations

    content related to news and information dissemination

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

    Technical terminology and domain-specific nouns within specialized contexts such as code, APIs, documentation, or technical fields.

    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
    ost
    -0.29
     Hy
    -0.28
    Su
    -0.28
    md
    -0.27
     walk
    -0.27
     modalidad
    -0.27
     run
    -0.26
     Gies
    -0.26
     heat
    -0.26
     løpet
    -0.26
    POSITIVE LOGITS
    AndEndTag
    0.90
    TagMode
    0.85
    SourceChecksum
    0.72
    fjspx
    0.71
     تضيفلها
    0.71
    IUrlHelper
    0.70
    spesies
    0.68
    niſſe
    0.68
     NSCoder
    0.68
     CURIAM
    0.67
    Activations Density 0.126%

    No Known Activations