© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 111785
    Prev
    Next
    INDEX
    Explanations

    references to government meetings and intelligence briefings

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

    drone strike missile attacks

    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
    ďaka
    -0.52
     TextAppearance
    -0.44
     Konkurrenz
    -0.43
     bénévoles
    -0.42
     desgracia
    -0.42
     convite
    -0.38
     düğün
    -0.38
     favoritos
    -0.38
     invierno
    -0.38
     perjuangan
    -0.37
    POSITIVE LOGITS
     detected
    0.63
    detected
    0.59
     airspace
    0.57
     intercepted
    0.56
     unarmed
    0.54
     Pentagon
    0.53
     unmanned
    0.52
    RenderAtEndOf
    0.52
     Detected
    0.51
    vereignty
    0.51
    Activations Density 0.023%

    No Known Activations