© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 12138
    Prev
    Next
    INDEX
    Explanations

    affirmative and active indicators within a context or code

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

    true, false, on, off

    np_acts-logits-general · gemini-2.5-flash-lite

    statements or configuration flags indicating an enabled/affirmative or universal setting in code and markup.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     utafitiHapana
    -0.65
     ErrIntOverflow
    -0.65
     MainAxisSize
    -0.63
     незавершена
    -0.57
    endphp
    -0.57
     snippetHide
    -0.57
    sack
    -0.57
     EconPapers
    -0.57
     Geiſt
    -0.56
    endforeach
    -0.55
    POSITIVE LOGITS
    AnimationsModule
    0.36
    especially
    0.29
     and
    0.28
    styleType
    0.28
    並且
    0.28
     costumi
    0.28
    medel
    0.27
    medium
    0.26
    乾淨
    0.26
    liceerd
    0.26
    Activations Density 0.001%

    No Known Activations