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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 10975
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "check" and its variations in the context of verification or examination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppCodeGen
    -0.47
    protoimpl
    -0.45
    haikusbot
    -0.39
     quoque
    -0.39
     getItemId
    -0.38
    didSet
    -0.37
     beroep
    -0.37
     voordeel
    -0.36
    localctx
    -0.35
    webElementXpaths
    -0.35
    POSITIVE LOGITS
     Check
    0.70
     CHECK
    0.68
     check
    0.65
    mate
    0.64
    boxes
    0.63
    Check
    0.63
     chk
    0.59
    check
    0.59
     checkers
    0.57
     Checking
    0.56
    Activations Density 0.060%

    No Known Activations