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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3287
    Prev
    Next
    INDEX
    Explanations

    references to United States laws or regulations

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

    legal citations, specifically U.S. legal references like U.S. Code sections and case law identifiers.

    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
     zoude
    -0.83
     dezelve
    -0.83
    ulongan
    -0.76
     própri
    -0.71
     wikipagina
    -0.71
     صوتيه
    -0.71
    arangay
    -0.69
     miniaturka
    -0.69
     sprüche
    -0.68
    alakip
    -0.68
    POSITIVE LOGITS
    <bos>
    0.76
    F
    0.58
    R
    0.56
    M
    0.52
    L
    0.51
    p
    0.51
    H
    0.50
    W
    0.50
    S
    0.50
    C
    0.50
    Activations Density 0.196%

    No Known Activations