© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 20596
    Prev
    Next
    INDEX
    Explanations

    sports-related performance indicators

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

    second level defense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    verkehr
    -0.36
     space
    -0.33
     Vía
    -0.32
    곤
    -0.32
    savefig
    -0.32
    Vía
    -0.31
    vspace
    -0.30
    raum
    -0.30
     spherical
    -0.29
     depend
    -0.29
    POSITIVE LOGITS
     reserve
    0.73
     reserves
    0.72
     backups
    0.71
     Reserves
    0.70
    reserve
    0.68
    Reserve
    0.68
     Reserve
    0.67
     rezerv
    0.66
     Reserv
    0.66
     rezer
    0.65
    Activations Density 0.021%

    No Known Activations