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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 723
    Prev
    Next
    INDEX
    Explanations

    function definitions and related programming constructs within code

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

    Code properties/methods (e.g., "node properties", "getInfo")

    np_acts-logits-general · gemini-2.0-flash

    astNode methods

    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
    IUrlHelper
    -0.63
    featureID
    -0.62
    parsedMessage
    -0.50
    XmlAccessType
    -0.48
    QMetaType
    -0.47
    PMailer
    -0.47
    writeField
    -0.46
    WriteBarrier
    -0.45
    utilisons
    -0.44
    istoitu
    -0.43
    POSITIVE LOGITS
     supposedly
    0.50
     متحده
    0.48
     theory
    0.47
     theoretically
    0.47
     colgante
    0.46
    Boris
    0.44
    Theory
    0.43
     Tunisie
    0.43
     purported
    0.42
     THEORY
    0.42
    Activations Density 0.664%

    No Known Activations