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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12177
    Prev
    Next
    INDEX
    Explanations

    specific mentions of clothing items and related context in legal discussions

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

    specific nouns and proper nouns that are central to the narrative or argument being presented.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    narrative descriptions of events, particularly violent or dramatic incidents involving people and their actions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    specialized, domain-specific language and notation—especially legal, medical/scientific, technical/engineering, mathematical, and programming terms in formal or procedural contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     nakalista
    -0.58
     &___
    -0.56
     autorytatywna
    -0.50
     Infórmanos
    -0.50
     Njema
    -0.50
     setempat
    -0.48
     AUSSI
    -0.48
     Italij
    -0.47
    šanās
    -0.47
     câncer
    -0.45
    POSITIVE LOGITS
    ➯
    0.58
    AddHtmlAttribute
    0.57
    Referanser
    0.49
    gradle
    0.47
    postsleuth
    0.47
    encodeWith
    0.47
    makeText
    0.46
    ⤹
    0.46
     endforeach
    0.44
     gra
    0.44
    Activations Density 8.904%

    No Known Activations