© 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. 6953
    Prev
    Next
    INDEX
    Explanations

    HTML and table-related elements in markup language

    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
     CreateTagHelper
    -0.56
     otomatig
    -0.53
    ftagPool
    -0.52
    pushFollow
    -0.52
    RTSC
    -0.44
    CompleteListener
    -0.43
    DECREF
    -0.43
    oredCriteria
    -0.42
     modelling
    -0.41
    forName
    -0.41
    POSITIVE LOGITS
    dymyr
    0.43
     Anſ
    0.43
    Mostly
    0.42
     balles
    0.42
     CURIAM
    0.41
    ConstraintMaker
    0.41
    SuppressLint
    0.40
    }]);
    0.39
    География
    0.39
    Cell
    0.39
    Activations Density 0.086%

    No Known Activations