© 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. 2372
    Prev
    Next
    INDEX
    Explanations

    collocations involving the prefix 'co-' that relate to cooperation and coordination

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

    terms related to professional coordination and collaboration.

    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
    marvin
    -0.56
    URLException
    -0.48
    ableView
    -0.46
    fulness
    -0.46
    <h2>
    -0.45
    setPreferredSize
    -0.45
     Blumen
    -0.45
    Rujuakan
    -0.45
     Peque
    -0.45
    PerformLayout
    -0.44
    POSITIVE LOGITS
     Co
    0.88
    Co
    0.86
     co
    0.84
    CoA
    0.71
    CO
    0.71
    co
    0.69
     Coen
    0.67
     CO
    0.67
     Coliseum
    0.66
    Cof
    0.66
    Activations Density 0.149%

    No Known Activations