© 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. 24-GEMMASCOPE-RES-16K
    11. 2079
    Prev
    Next
    INDEX
    Explanations

    dialogue or conversational elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Common French verbs/expressions

    np_acts-logits-general · gemini-2.0-flash

    french or spanish verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.79
    Personensuche
    -0.70
    SourceChecksum
    -0.69
    ConstraintMaker
    -0.68
    TypedDataSet
    -0.66
    findpost
    -0.65
     يتيمه
    -0.61
    Personendaten
    -0.61
    contentLoaded
    -0.60
    sizeCache
    -0.60
    POSITIVE LOGITS
     loot
    0.37
     bud
    0.33
     crazy
    0.33
    Class
    0.33
    !
    0.33
    ocracy
    0.32
    Dragging
    0.32
     that
    0.31
     EVERYTHING
    0.31
     stupid
    0.30
    Activations Density 0.305%

    No Known Activations