© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 58540
    Prev
    Next
    INDEX
    Explanations

    references to layout parameter settings in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     ویکی‌پدی
    -0.42
    tinyos
    -0.39
    czer
    -0.38
    Enllaces
    -0.36
    Naval
    -0.36
    Wester
    -0.35
    SharedDtor
    -0.35
    pä
    -0.35
    endforeach
    -0.35
     validés
    -0.35
    POSITIVE LOGITS
    LayoutParams
    2.41
    BagConstraints
    1.18
    layoutParams
    1.05
    setLayoutParams
    0.86
    PullParser
    0.71
     InputDecoration
    0.68
    prepareStatement
    0.67
     للاسماء
    0.65
    DockStyle
    0.63
    PerformLayout
    0.62
    Activations Density 0.001%

    No Known Activations