© 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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 13510
    Prev
    Next
    INDEX
    Explanations

    health-related risks associated with exposure to toxic substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.92
    anskje
    -0.92
    IsContent
    -0.83
    awtextra
    -0.83
    脚注の使い方
    -0.77
    хьтан
    -0.77
    :✨
    -0.76
    
    -0.76
     nahilalakip
    -0.75
     calendriers
    -0.72
    POSITIVE LOGITS
     excess
    0.81
     excessive
    0.77
    Excess
    0.72
     Excess
    0.65
     prolonged
    0.64
     Excessive
    0.63
    Excessive
    0.59
     exposure
    0.59
    excess
    0.57
     exces
    0.54
    Activations Density 0.713%

    No Known Activations