© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 82724
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "check" and its variants in the context of validation processes

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

    check and Checker

    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
    sterdam
    -0.54
     voordeel
    -0.54
    getMinutes
    -0.54
     newUser
    -0.53
     SOA
    -0.53
     fileSize
    -0.52
     imageUrl
    -0.52
    initialState
    -0.52
    oas
    -0.52
    tschaft
    -0.50
    POSITIVE LOGITS
    Check
    1.21
    check
    1.20
     Check
    1.19
     check
    1.13
     CHECK
    1.06
    CHECK
    1.00
     Checks
    0.88
     Checker
    0.87
     checks
    0.86
    Checker
    0.82
    Activations Density 0.018%

    No Known Activations