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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 103132
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "have."

    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
    bufio
    -0.41
    ToDecimal
    -0.34
    fontStyle
    -0.33
    IconModule
    -0.33
    else
    -0.32
    */
    -0.31
     itſelf
    -0.30
    $*$
    -0.29
    fromLTRB
    -0.29
     jap
    -0.29
    POSITIVE LOGITS
     have
    1.09
     had
    1.02
    have
    1.02
     been
    1.02
     has
    0.91
    Have
    0.87
    setHas
    0.86
    有过
    0.85
     memiliki
    0.85
    had
    0.84
    Activations Density 0.230%

    No Known Activations