© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102607
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and concepts related to programming and engineering

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

    The token "<<<bos>>>" marks the beginning of a new document or text segment across various types of content.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    TagMode
    -0.91
    AddTagHelper
    -0.85
    complexContent
    -0.82
     виправивши
    -0.81
    enumii
    -0.77
     disambiguazione
    -0.76
     NSCoder
    -0.75
    Datuak
    -0.74
     CreateTagHelper
    -0.73
    ConstraintMaker
    -0.70
    POSITIVE LOGITS
    Читати
    0.35
    Referències
    0.32
     nok
    0.31
     RG
    0.30
    Facebook
    0.29
     kor
    0.29
    riezmann
    0.29
    『
    0.28
    jonijiet
    0.28
     «
    0.28
    Activations Density 1.767%

    No Known Activations