© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 900
    Prev
    Next
    INDEX
    Explanations

    concepts related to data management and processing techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     provisoire
    -0.39
    prefixer
    -0.37
     etmeye
    -0.34
     zpě
    -0.33
     perasaan
    -0.32
     Nachfrage
    -0.31
     kaupung
    -0.31
     prů
    -0.31
     kautta
    -0.30
    makeConstraints
    -0.30
    POSITIVE LOGITS
     disambiguazione
    0.62
    featureID
    0.58
     OFDb
    0.57
    principalColumn
    0.57
    IndentedString
    0.56
    RegressionTest
    0.54
     setCode
    0.54
     getLayout
    0.53
    aarrggbb
    0.53
    windowFixed
    0.52
    Activations Density 1.106%

    No Known Activations