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. 113993
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions, specifically referencing "ce" as part of various medical terminologies and conditions

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

    celiac disease or cementation

    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
     newspaper
    -0.50
     Timoteo
    -0.48
     Unidas
    -0.48
     armée
    -0.46
    domés
    -0.46
     Stringer
    -0.45
     Bakker
    -0.45
     the
    -0.44
    woli
    -0.44
     aggressive
    -0.44
    POSITIVE LOGITS
    Ce
    0.91
     CE
    0.88
    CE
    0.84
     Ce
    0.82
    ce
    0.82
     ce
    0.81
     Ceb
    0.76
    cey
    0.72
    ceta
    0.72
     Cep
    0.71
    Activations Density 0.037%

    No Known Activations