© 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 - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3392
    Prev
    Next
    INDEX
    Explanations

    questions and statements related to mathematical concepts or operations

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

    list items marked with asterisks or numbered sequences.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
    Personendaten
    -0.72
    WebElementEntity
    -0.68
     surla
    -0.66
     estekak
    -0.64
     betweenstory
    -0.64
    Vidite
    -0.63
     للاسماء
    -0.63
    хьтан
    -0.63
    adaptiveStyles
    -0.61
     CanadaChoose
    -0.60
    POSITIVE LOGITS
     herói
    0.40
     governador
    0.35
    rungsseite
    0.34
     acteurs
    0.33
     jornalista
    0.31
     devrez
    0.31
    ↵↵
    0.30
    ポーター
    0.30
    griffen
    0.29
     devons
    0.29
    Activations Density 0.146%

    No Known Activations