© 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. 38945
    Prev
    Next
    INDEX
    Explanations

    occurrences of conflict and violence-related actions and events

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

    attack and raid actions

    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
    хьтан
    -0.42
    ContextHolder
    -0.34
    ticket
    -0.32
     guantes
    -0.32
    tvguidetime
    -0.32
     boletos
    -0.32
     rū
    -0.31
     comportements
    -0.31
     łyż
    -0.31
    MENAFN
    -0.31
    POSITIVE LOGITS
     attack
    1.95
     attacks
    1.77
    attack
    1.68
     attacked
    1.66
     Attack
    1.57
     ATTACK
    1.55
     Attacks
    1.54
    Attack
    1.53
     raid
    1.53
    attacks
    1.52
    Activations Density 0.135%

    No Known Activations