© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 107736
    Prev
    Next
    INDEX
    Explanations

    code structure and elements related to privacy and access control in programming

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

    private member declarations

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     CURIAM
    -0.64
    cifix
    -0.55
    AddTagHelper
    -0.55
     arşivlendi
    -0.51
    insegna
    -0.47
     quoc
    -0.47
    rsiniz
    -0.46
    |};
    -0.45
    middels
    -0.45
    ksikon
    -0.45
    POSITIVE LOGITS
    simpleType
    0.52
    private
    0.36
    الحياه
    0.35
    Derbyniad
    0.35
    הערות
    0.35
    otechnical
    0.33
     Савезне
    0.32
    BindingResult
    0.31
     PagesJaunes
    0.30
     Batt
    0.30
    Activations Density 0.008%

    No Known Activations