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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 7404
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to medical imaging techniques

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

    Technical instruments, tools, and methodologies used for observation, analysis or measurement in scientific, medical or professional contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Personensuche
    -0.57
     LoginComponent
    -0.48
    ckså
    -0.44
     Interest
    -0.43
    Interest
    -0.43
    SOUNDBITE
    -0.42
    ýt
    -0.42
     فريبيس
    -0.41
    Organisateur
    -0.41
    UrlResolution
    -0.41
    POSITIVE LOGITS
    قایناق‌لار
    0.39
     rebajas
    0.39
     الحره
    0.37
    barrow
    0.37
    LOYEES
    0.36
    SharedDtor
    0.35
     llorando
    0.35
    WireFormatLite
    0.35
    rifuge
    0.35
     Wrang
    0.35
    Activations Density 0.355%

    No Known Activations