© 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
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 11810
    Prev
    Next
    INDEX
    Explanations

    technical terms related to methodologies and processes

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

    technical or formal instructional language that provides procedural guidance, specifications, or detailed explanations, particularly in academic, legal, or technical documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    formal academic or technical boilerplate about document structure, methods and step-by-step procedures, citation/reference and publication notices, and administrative review or rule statements.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.45
     surla
    -0.43
    
    -0.41
     esternos
    -0.40
     UITableViewCell
    -0.35
    ⁣⁣
    -0.34
    ⁣
    -0.31
    wpi
    -0.31
    HasAnnotation
    -0.30
     //$
    -0.30
    POSITIVE LOGITS
     nonUne
    0.75
    verifyException
    0.73
     pageContext
    0.71
     noDo
    0.66
     EconPapers
    0.65
    AutoScaleMode
    0.64
    ValueStyle
    0.62
    InjectAttribute
    0.62
    ViewImports
    0.61
     ویکی‌پدی
    0.60
    Activations Density 23.881%

    No Known Activations