© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 16395
    Prev
    Next
    INDEX
    Explanations

    quotes and citations in the text

    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
     kasarigan
    -0.65
    SharedDtor
    -0.65
    UrlResolution
    -0.61
    jsonwebtoken
    -0.60
    RenderAtEndOf
    -0.57
    رشف
    -0.56
     OFDb
    -0.56
    CppMethod
    -0.56
     estekak
    -0.56
     BoxFit
    -0.56
    POSITIVE LOGITS
     posiad
    0.34
     deemed
    0.34
     biais
    0.33
     deems
    0.33
    SuppressLint
    0.33
     pienso
    0.33
     answers
    0.32
     regarding
    0.31
     unido
    0.31
     makeStyles
    0.31
    Activations Density 0.007%

    No Known Activations