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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3831
    Prev
    Next
    INDEX
    Explanations

    functions and methods related to checking conditions and validating data

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

    Code related to boolean checks

    np_acts-logits-general · gemini-2.0-flash

    check followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thiệu
    -0.42
     gjerne
    -0.41
    gaande
    -0.41
     préférences
    -0.36
     собі
    -0.35
    argout
    -0.35
    mulo
    -0.34
    getOut
    -0.34
    地说道
    -0.33
    Demikian
    -0.33
    POSITIVE LOGITS
     check
    0.96
    check
    0.92
     Check
    0.84
     checks
    0.82
    Check
    0.82
     checker
    0.81
     checking
    0.78
     CHECK
    0.77
    Checker
    0.76
    checker
    0.76
    Activations Density 0.348%

    No Known Activations