Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 45900
    Prev
    Next
    INDEX
    Explanations

    references to research and development (R&D) in the context of scientific programs and initiatives

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

    R&D performer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     dezelve
    -1.02
     plufieurs
    -1.02
     zoude
    -0.99
     desmotivaciones
    -0.94
     zijne
    -0.88
     feroit
    -0.87
    zelfde
    -0.83
     miniaturka
    -0.83
    arangay
    -0.83
     Verſ
    -0.82
    POSITIVE LOGITS
    <bos>
    0.74
    B
    0.62
     R
    0.59
    R
    0.59
     C
    0.59
     B
    0.59
    N
    0.58
    H
    0.58
    M
    0.57
    J
    0.57
    Activations Density 0.025%

    No Known Activations