© 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 EvalsExportsAPI 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. 3308
    Prev
    Next
    INDEX
    Explanations

    phrases related to questioning and challenging the status quo

    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
    Geplaatst
    -0.65
    ांकि
    -0.53
    Portail
    -0.52
    alakip
    -0.51
    latego
    -0.50
     архивлан
    -0.50
    Referències
    -0.50
    AddHtmlAttribute
    -0.49
    脚注の使い方
    -0.49
    ostante
    -0.48
    POSITIVE LOGITS
    ViewFeatures
    0.41
     eventId
    0.34
     others
    0.34
     mAdapter
    0.33
     Lins
    0.33
     resultList
    0.32
     disambiguazione
    0.31
    ClassId
    0.31
    isNameExpr
    0.30
    CppMethod
    0.30
    Activations Density 0.407%

    No Known Activations