© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1200
    Prev
    Next
    INDEX
    Explanations

    suggestions for improvements or clarifications

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

    usefulness or benefit

    np_acts-logits-general · gemini-2.0-flash

    useful or advisable

    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
    Tikang
    -0.55
     VIDEOTAPE
    -0.53
    脚注の使い方
    -0.50
    etlen
    -0.48
    DropColumn
    -0.47
     Allociné
    -0.47
     Gegenteil
    -0.47
    tagHelperRunner
    -0.47
     stehe
    -0.46
     müsste
    -0.46
    POSITIVE LOGITS
     worth
    0.95
     good
    0.93
     worthwhile
    0.92
     advisable
    0.92
     wise
    0.90
     prudent
    0.89
     helpful
    0.88
     useful
    0.88
     Worth
    0.80
    useful
    0.79
    Activations Density 0.236%

    No Known Activations