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. 8195
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references in discourse

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

    Punctuation (especially periods) at the end of sentences that conclude statements referencing previous work, findings, or content.

    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
    aarrggbb
    -0.63
     HFILL
    -0.53
    лтамалар
    -0.49
    IBOutlet
    -0.46
     للاسماء
    -0.46
    таратура
    -0.46
     Drapeau
    -0.44
    RenderAtEndOf
    -0.44
    GEBURTSDATUM
    -0.44
    usercontent
    -0.43
    POSITIVE LOGITS
     now
    0.48
    ngrx
    0.38
    MouseAdapter
    0.36
     pulumi
    0.35
     CanadaChoose
    0.35
    autoconfigure
    0.35
    XmlAccessType
    0.35
    Buenos
    0.35
    PROXY
    0.35
    ulose
    0.34
    Activations Density 0.069%

    No Known Activations