© 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. 24-GEMMASCOPE-RES-16K
    11. 10822
    Prev
    Next
    INDEX
    Explanations

    function and method calls in a programming context

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

    Code related to drawing or parsing

    np_acts-logits-general · gemini-2.0-flash

    draw, parse, run, query

    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
    parsedMessage
    -0.78
    󠁮
    -0.70
    ſammen
    -0.68
     HasFactory
    -0.66
     ujednoznacz
    -0.66
    usermodel
    -0.65
    stateProvider
    -0.65
    MigrationBuilder
    -0.63
    LookAnd
    -0.63
     propOrder
    -0.63
    POSITIVE LOGITS
    Hozzáférés
    0.41
     read
    0.40
     induced
    0.38
    øs
    0.37
     set
    0.37
     directly
    0.37
     cross
    0.36
     using
    0.36
     (
    0.35
     direct
    0.34
    Activations Density 0.294%

    No Known Activations