© 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. 10520
    Prev
    Next
    INDEX
    Explanations

    textual references and citations in legal or academic documents

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

    legal citation references and footnote markers.

    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
     للاسماء
    -0.76
     ModelExpression
    -0.69
    Personendaten
    -0.62
    Portale
    -0.59
    tagHelperRunner
    -0.57
    awtextra
    -0.55
    Portail
    -0.54
    Personensuche
    -0.54
    UrlResolution
    -0.54
     Exactos
    -0.54
    POSITIVE LOGITS
     notes
    2.33
     note
    2.28
     Notes
    2.09
    Notes
    2.08
    notes
    2.00
    note
    1.88
     NOTES
    1.85
     Note
    1.83
    NOTES
    1.80
    Note
    1.74
    Activations Density 0.851%

    No Known Activations