© 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. 20-GEMMASCOPE-RES-16K
    11. 5523
    Prev
    Next
    INDEX
    Explanations

    references to tabs and tagging systems, particularly in programming or user interface contexts

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

    programming-related terms and code syntax, particularly HTML, CSS, and programming language elements like "tab" and other technical tokens.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    TemporalType
    -0.46
    WEBPACK
    -0.46
    Biografie
    -0.45
    heres
    -0.45
    levi
    -0.45
    hera
    -0.42
    ostante
    -0.41
    Życiorys
    -0.41
     Schaefer
    -0.41
    )));
    -0.41
    POSITIVE LOGITS
     spot
    0.79
    spot
    0.75
     spots
    0.73
    spots
    0.73
    Spot
    0.71
    WithTag
    0.70
     Spot
    0.69
    Tag
    0.68
     tag
    0.68
     SPOT
    0.68
    Activations Density 0.199%

    No Known Activations