© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9080
    Prev
    Next
    INDEX
    Explanations

    structured data formats and mathematical notations

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

    line breaks and formatting characters in code or mathematical notation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    Clik
    -0.36
     ویکی‌پدی
    -0.34
    ftagPool
    -0.33
     CanadaChoose
    -0.29
     utafitiHapana
    -0.28
    皆さま
    -0.28
    Välislingid
    -0.27
    こともある
    -0.27
     mp
    -0.26
    nalités
    -0.26
    POSITIVE LOGITS
     AssemblyTitle
    0.53
     Autorizaciones
    0.51
     betweenstory
    0.51
    webElementXpaths
    0.50
    botines
    0.50
    RectangleBorder
    0.49
    addPreferredGap
    0.48
    InjectAttribute
    0.48
    clusal
    0.47
     Pingback
    0.47
    Activations Density 1.037%

    No Known Activations