© 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. 15-GEMMASCOPE-RES-16K
    6. 12597
    Prev
    Next
    INDEX
    Explanations

    references to components, actions, or roles in complex systems or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.54
    IGraphics
    -0.54
    ValueStyle
    -0.52
    pyx
    -0.49
    principalColumn
    -0.49
     אחת
    -0.49
     ogóle
    -0.48
     tambi
    -0.47
     useAppContext
    -0.47
     ferner
    -0.47
    POSITIVE LOGITS
     remaining
    0.86
     rest
    0.83
     Remaining
    0.82
    rest
    0.76
    Remaining
    0.71
     pozosta
    0.70
     restante
    0.70
     reste
    0.69
     restantes
    0.68
    remaining
    0.68
    Activations Density 0.490%

    No Known Activations