© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 14288
    Prev
    Next
    INDEX
    Explanations

    references to physical violence and aggression

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

    Hit/punched in a body part

    np_acts-logits-general · gemini-2.0-flash

    hitting body parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    İstinadlar
    -0.45
    Cyfeiriadau
    -0.45
     StringVar
    -0.44
     hô
    -0.44
    lixir
    -0.44
    end
    -0.44
    ciech
    -0.44
    ChildScrollView
    -0.44
    tonode
    -0.43
     Draft
    -0.43
    POSITIVE LOGITS
     forehead
    0.78
     head
    0.72
    ReusableCell
    0.65
    исленность
    0.63
    bootstrapcdn
    0.61
     headshot
    0.59
     ***!
    0.58
     squarely
    0.58
     face
    0.57
     chest
    0.56
    Activations Density 0.097%

    No Known Activations