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. 29289
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "strict" and related variations indicating rigidity or high standards

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

    strict/strictly usage

    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
    MEA
    -0.59
    Edison
    -0.56
     Popcorn
    -0.56
     userID
    -0.55
     currentValue
    -0.55
    COA
    -0.54
     NEM
    -0.54
     Selfie
    -0.53
     getItemId
    -0.53
    Enlaces
    -0.52
    POSITIVE LOGITS
     strict
    1.07
    strict
    0.96
     strictly
    0.96
     Strict
    0.93
    Strict
    0.88
    Strictly
    0.81
     estric
    0.80
     Strictly
    0.79
     estrictamente
    0.72
     ketat
    0.72
    Activations Density 0.008%

    No Known Activations