© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 12573
    Prev
    Next
    INDEX
    Explanations

    terms related to medical diagnostics and test results

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

    MEC, OU, RS, AD, VC, NM, FR, SE

    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
     very
    -0.44
     pièce
    -0.31
    very
    -0.29
     mess
    -0.29
     contigo
    -0.29
     alvor
    -0.29
     most
    -0.29
     more
    -0.28
     last
    -0.28
    <strong>
    -0.28
    POSITIVE LOGITS
     betweenstory
    0.98
    ValueStyle
    0.96
     autorytatywna
    0.95
    Personensuche
    0.93
    UserScript
    0.89
    expandindo
    0.85
     MainAxisSize
    0.85
    Autoritní
    0.84
    ésultats
    0.83
    Datuak
    0.81
    Activations Density 0.450%

    No Known Activations