© 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 EvalsExportsinterp-engineNEWAPI 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. 4413
    Prev
    Next
    INDEX
    Explanations

    references to locations or geographical entities

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

    French words and phrases, particularly prepositions and articles like "du," "au," "le," and "la."

    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
     doméstica
    -0.46
     voeten
    -0.40
    FIELDS
    -0.38
    ște
    -0.38
     löytyy
    -0.38
     Bäume
    -0.35
    ține
    -0.35
     paljon
    -0.35
     Schulen
    -0.34
     Füße
    -0.34
    POSITIVE LOGITS
    parsedMessage
    0.91
    MigrationBuilder
    0.83
    rungsseite
    0.82
    ImageContext
    0.82
    tvguidetime
    0.82
     itſelf
    0.79
    WireFormatLite
    0.75
     bershka
    0.74
    ロウィン
    0.73
     myſelf
    0.73
    Activations Density 0.061%

    No Known Activations