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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 24590
    Prev
    Next
    INDEX
    Explanations

    specific medical conditions, treatments, or procedures related to health evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    nEnter
    -0.41
    .*")]
    -0.40
     Sicilia
    -0.39
    StructField
    -0.38
     impact
    -0.38
     Pen
    -0.38
     pen
    -0.37
    IBarButtonItem
    -0.37
    biendo
    -0.37
     кӀ
    -0.37
    POSITIVE LOGITS
    styleType
    0.44
     tả
    0.44
     HttpNotFound
    0.44
     pouvoit
    0.42
    engagent
    0.42
    GOTREF
    0.41
    گاب
    0.41
    stateMutability
    0.41
    lüğü
    0.39
    TryDecodeAsNil
    0.39
    Activations Density 0.082%

    No Known Activations