© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 76428
    Prev
    Next
    INDEX
    Explanations

    declarations of classes and their visibility modifiers within code

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

    access modifiers like internal, private, static

    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
    liferay
    -0.45
     препратки
    -0.44
     дописавши
    -0.39
    IntoConstraints
    -0.38
    errHandler
    -0.37
    openqa
    -0.37
    AsUp
    -0.36
    mphony
    -0.36
     فريبيس
    -0.35
    Clik
    -0.35
    POSITIVE LOGITS
    internal
    0.61
    interopRequire
    0.52
    期刊论文
    0.52
    Internal
    0.49
     navideño
    0.47
    Personensuche
    0.46
    fileprivate
    0.45
     Administrativna
    0.45
    Diwedd
    0.45
     internal
    0.44
    Activations Density 0.002%

    No Known Activations