© 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. 17-GEMMASCOPE-RES-16K
    11. 6895
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific analysis and experimentation

    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
    asantry
    -0.82
    aratus
    -0.72
     MenuView
    -0.70
    aptation
    -0.69
    ofition
    -0.68
    ttemberg
    -0.64
    ercises
    -0.62
    orthand
    -0.62
    haustible
    -0.61
    prits
    -0.61
    POSITIVE LOGITS
     nonUne
    0.61
    __).
    0.60
    
    0.59
    <bos>
    0.59
    ostante
    0.58
      
    0.57
    ous
    0.56
    CodeAttribute
    0.56
    ir
    0.54
    
    0.54
    Activations Density 0.354%

    No Known Activations