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

    Neuronpedia

    APICircuit 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. 8997
    Prev
    Next
    INDEX
    Explanations

    keywords related to healthcare, diagnostics, and patient management

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

    medical treatment and biological entities

    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
    zzleHttp
    -0.53
     Numerade
    -0.51
    حوالہ
    -0.51
    SerializedName
    -0.47
     kaarangay
    -0.47
     InputDecoration
    -0.47
    Personendaten
    -0.47
    oredCriteria
    -0.47
    ficulty
    -0.46
     мәгълү
    -0.46
    POSITIVE LOGITS
     Internasional
    0.39
     enkelte
    0.37
    Cordialement
    0.37
     Töchter
    0.37
     disambiguazione
    0.36
     ślub
    0.35
    MarshalTo
    0.35
    整體
    0.34
     gewissen
    0.34
     Menschheit
    0.34
    Activations Density 0.098%

    No Known Activations