© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 507
    Prev
    Next
    INDEX
    Explanations

    punctuation, specifically periods

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

    periods and blank lines

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

    various commands and structures

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ⇑
    -0.52
     endwhile
    -0.48
    ,
    -0.46
    ?
    -0.46
     -
    -0.41
    یرات
    -0.41
    >>>
    -0.41
    @[+][
    -0.40
    endmodule
    -0.40
    endif
    -0.40
    POSITIVE LOGITS
    AutoScale
    0.91
    })*/
    0.83
     depositphotos
    0.80
    UIControlState
    0.78
    ſelf
    0.75
     Majefty
    0.75
     Shakspeare
    0.74
     Efq
    0.73
     themſelves
    0.73
     purpoſe
    0.72
    Activations Density 0.002%

    No Known Activations