© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 588
    Prev
    Next
    INDEX
    Explanations

    class and function declarations related to UI and file handling in programming

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

    Java import statements

    np_acts-logits-general · gemini-2.0-flash

    code and programming libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.66
    #![
    -0.63
    setViewportView
    -0.61
    ComponentModel
    -0.60
    numerusform
    -0.55
     astore
    -0.55
    werfer
    -0.55
     Seidel
    -0.55
     Espinosa
    -0.54
     bubble
    -0.53
    POSITIVE LOGITS
    IntoConstraints
    0.47
     resourceCulture
    0.43
     nakalista
    0.37
    LabelTagHelper
    0.35
    DeleteBehavior
    0.34
     ModelExpression
    0.33
    adaptiveStyles
    0.32
    AutoField
    0.32
    cstdio
    0.30
     fabricants
    0.30
    Activations Density 0.014%

    No Known Activations