© 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. 112677
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and user interface operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    impresa
    -0.46
    jdzie
    -0.45
     Pedersen
    -0.44
    期刊论文
    -0.43
    RenderAtEndOf
    -0.43
    TokenNameLPAREN
    -0.43
     afspraak
    -0.43
     Kindes
    -0.42
    iseta
    -0.42
    eseorang
    -0.41
    POSITIVE LOGITS
    Diwedd
    0.68
     informée
    0.66
     незавершена
    0.66
    LookAnd
    0.63
     Roskov
    0.62
    Gweler
    0.59
    ">//
    0.59
    تقاوى
    0.54
     surla
    0.54
     propOrder
    0.54
    Activations Density 0.004%

    No Known Activations