© 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. 20-GEMMASCOPE-RES-16K
    11. 348
    Prev
    Next
    INDEX
    Explanations

    formatting tags, particularly those indicating emphasis or italics

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

    HTML formatting tags

    np_acts-logits-general · gemini-2.0-flash

    codes and specific references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </b>
    -0.68
    Autoritní
    -0.62
    <eos>
    -0.61
    asteroide
    -0.56
    }{
    -0.54
    】：
    -0.54
    arakhand
    -0.51
     
    -0.51
    dı
    -0.51
     dos
    -0.51
    POSITIVE LOGITS
    </em>
    1.37
    </i>
    1.00
    </h6>
    0.91
     contextLoads
    0.89
    rrggbb
    0.87
     Saltar
    0.86
     itſelf
    0.85
     myſelf
    0.84
     ་་
    0.82
     confé
    0.80
    Activations Density 0.041%

    No Known Activations