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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 5761
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "find" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oquia
    -0.65
    gawai
    -0.58
     
    -0.58
    OPERATOR
    -0.56
    kowych
    -0.55
     отношению
    -0.53
    UserProfile
    -0.53
    crans
    -0.52
    closeButton
    -0.51
    shtml
    -0.50
    POSITIVE LOGITS
     Findlay
    1.53
     FIND
    1.23
    FIND
    1.23
    find
    1.13
     Finds
    1.06
    Find
    1.06
    :✨
    1.03
     Find
    0.99
     doInBackground
    0.98
    findElement
    0.96
    Activations Density 0.071%

    No Known Activations