© 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. 500
    Prev
    Next
    INDEX
    Explanations

    comments and annotations in coding or programming contexts

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

    comment syntax and percentage values in programming or script-related texts

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

    code actions after comments

    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
     figliu
    -0.75
     mourut
    -0.67
     ciasc
    -0.65
     ciascuno
    -0.63
     esistono
    -0.62
     spirituale
    -0.60
     casó
    -0.59
     sepol
    -0.59
     forskj
    -0.59
    UnknownFields
    -0.58
    POSITIVE LOGITS
     get
    0.75
     بيها
    0.74
     check
    0.71
     turn
    0.71
     increase
    0.65
     put
    0.64
     add
    0.64
     don
    0.63
     set
    0.63
     dont
    0.63
    Activations Density 0.026%

    No Known Activations