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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 68367
    Prev
    Next
    INDEX
    Explanations

    terms associated with violent or controversial actions and their justifications

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

    dismemberment, decapitation, slaughter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.59
    Personendaten
    -0.58
    SuccessListener
    -0.52
    ⓧ
    -0.49
    Chham
    -0.48
    ItemBackground
    -0.47
    testens
    -0.46
    Nazionale
    -0.44
    makeConstraints
    -0.44
    はじめに
    -0.44
    POSITIVE LOGITS
     mutilated
    0.92
     mutil
    0.90
     mangled
    0.56
     slaughter
    0.55
     decap
    0.54
     emas
    0.54
     Slaughter
    0.52
     butcher
    0.51
     beheaded
    0.51
     amputation
    0.48
    Activations Density 0.034%

    No Known Activations