© 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
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15382
    Prev
    Next
    INDEX
    Explanations

    elements related to murder and violent crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     boardwalk
    -0.50
     Seaside
    -0.49
    ⎣
    -0.47
    IsPostBack
    -0.46
    Chalk
    -0.46
    Beach
    -0.46
     Board
    -0.45
     Beach
    -0.45
    itec
    -0.45
     Kolle
    -0.45
    POSITIVE LOGITS
     kill
    1.37
     killing
    1.36
     Killing
    1.23
     Kill
    1.21
     kills
    1.21
     murder
    1.19
    killing
    1.19
     KILL
    1.17
    Kill
    1.17
     killed
    1.16
    Activations Density 0.247%

    No Known Activations