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

    Neuronpedia

    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. 41-GEMMASCOPE-RES-16K
    11. 10766
    Prev
    Next
    INDEX
    Explanations

    closing brackets or symbols in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.69
    ArrowToggle
    -0.55
    richTextPanel
    -0.53
    NameInMap
    -0.51
    DIPSETTING
    -0.49
    WriteTagHelper
    -0.49
    featureID
    -0.49
    lichter
    -0.48
    VersionUID
    -0.44
     snippetHide
    -0.44
    POSITIVE LOGITS
    internal
    0.83
    public
    0.80
     public
    0.78
     internal
    0.70
    [
    0.69
    private
    0.68
     [
    0.67
     private
    0.64
    readonly
    0.57
     partial
    0.55
    Activations Density 0.042%

    No Known Activations