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. 56394
    Prev
    Next
    INDEX
    Explanations

    references to healthcare and medical terminology

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

    experiencing transient experimental complications

    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
     kasarigan
    -0.69
    SharedDtor
    -0.60
    RTDA
    -0.56
    =$?
    -0.56
    jsxFileName
    -0.55
    sizeCache
    -0.54
    ngrx
    -0.54
     estimés
    -0.54
     giggled
    -0.53
    )
    
    
    -0.52
    POSITIVE LOGITS
     civilización
    0.44
     außerdem
    0.35
     inoltre
    0.35
    woor
    0.33
     utilización
    0.32
     supervivencia
    0.32
     zudem
    0.32
     infatti
    0.30
    gapan
    0.30
     therefore
    0.29
    Activations Density 0.117%

    No Known Activations