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

    Neuronpedia

    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. 15846
    Prev
    Next
    INDEX
    Explanations

    references to user verification or privacy policies

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

    non-English text tokens, particularly from Slavic languages like Croatian/Serbian.

    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
     ब्रेकडाउन
    -0.48
     otomatig
    -0.35
     Logs
    -0.35
    elerik
    -0.35
     kiệm
    -0.34
     saja
    -0.34
     Fraction
    -0.34
    rąg
    -0.34
    brtc
    -0.33
     utafitiHapana
    -0.33
    POSITIVE LOGITS
    UnknownFieldSet
    0.58
     ModelExpression
    0.52
    rungsseite
    0.52
    AnchorStyles
    0.45
    LEncoder
    0.45
     AspNetCore
    0.43
    XmlAccessType
    0.42
    ViewImports
    0.42
    UrlResolution
    0.42
    nameof
    0.41
    Activations Density 0.037%

    No Known Activations