© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 112839
    Prev
    Next
    INDEX
    Explanations

    closing braces and semicolons in code structures

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

    <ul><li>type</li><li>packet</li><li>context</li><li>`</li><li>structure</li></ul>

    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
     EconPapers
    -0.59
    TargetException
    -0.54
    onAttach
    -0.54
     <=",
    -0.54
    FXML
    -0.53
    ⟬
    -0.52
    ברס
    -0.52
    ✥
    -0.50
    afficheront
    -0.50
    FunctionFlags
    -0.49
    POSITIVE LOGITS
     disambiguazione
    0.43
    Notae
    0.40
    曖昧さ回避
    0.37
    corazón
    0.36
    exitRule
    0.34
    EndContext
    0.33
     avantage
    0.33
    Autoritní
    0.33
    toByteArray
    0.33
    
    0.33
    Activations Density 0.012%

    No Known Activations