© 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. 31-GEMMASCOPE-RES-16K
    11. 15032
    Prev
    Next
    INDEX
    Explanations

    elements and functions associated with event handling and requests in programming contexts

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

    function calls and method invocations with dot notation or arrow operators.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.82
     '\\;'
    -0.77
    aarrggbb
    -0.75
     laſſen
    -0.68
    +#+#
    -0.67
     CreateTagHelper
    -0.65
     müſſen
    -0.65
    RTLI
    -0.65
     ſeine
    -0.64
    niſſe
    -0.64
    POSITIVE LOGITS
     call
    0.76
    call
    0.68
    (
    0.60
     applied
    0.59
     Call
    0.56
    Invoke
    0.55
     (
    0.55
     executed
    0.54
     function
    0.52
    invoke
    0.49
    Activations Density 0.461%

    No Known Activations