© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7439
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical or programming structures

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

    tokens that look like formal identifiers—short capitalized math symbols and code/schema variable or type names (camelCase/underscore) in technical contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    variable names or identifiers, particularly single letters like "n", "N", "W", and "j" in mathematical or programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    tagHelperRunner
    -0.78
    bootstrapcdn
    -0.71
     betweenstory
    -0.67
    Tikang
    -0.64
    delwed
    -0.62
    ↹
    -0.62
    Autoritní
    -0.60
    Hentet
    -0.58
    AddTagHelper
    -0.57
    adaptiveStyles
    -0.57
    POSITIVE LOGITS
     Económica
    0.55
     dinámico
    0.47
     convocatoria
    0.47
     desconocido
    0.47
     económica
    0.45
     oscuridad
    0.45
     navideños
    0.44
     aislado
    0.44
     formales
    0.44
     controlado
    0.43
    Activations Density 0.584%

    No Known Activations