© 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. 19-GEMMASCOPE-RES-16K
    6. 3223
    Prev
    Next
    INDEX
    Explanations

    chemical and mathematical symbols or coefficients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $
    -0.57
    <sup>
    -0.53
    !*\
    -0.52
    }}_
    -0.51
     ${
    -0.50
     $\
    -0.50
     van
    -0.48
    sizeCache
    -0.48
    ani
    -0.47
    )))))
    -0.47
    POSITIVE LOGITS
     الحره
    0.89
     createStore
    0.80
    CGRectMake
    0.78
     تانيه
    0.76
     itſelf
    0.75
     Voyez
    0.74
     Partagez
    0.74
    קישורים
    0.74
     tubeless
    0.72
     ་་
    0.71
    Activations Density 0.773%

    No Known Activations