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. 20-GEMMASCOPE-RES-16K
    6. 1132
    Prev
    Next
    INDEX
    Explanations

    instances of the word "find" and its variations in the text

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

    Sentences containing the word "find"

    np_acts-logits-general · gemini-2.0-flash

    finding

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Schlegel
    -0.69
     deleteById
    -0.62
     Velasco
    -0.62
     endblock
    -0.61
     Berger
    -0.59
     roleId
    -0.59
    cademic
    -0.58
     Geſch
    -0.58
     سكانية
    -0.56
    deviceId
    -0.56
    POSITIVE LOGITS
    find
    1.13
    Find
    1.13
     find
    1.10
     Find
    1.10
     FIND
    1.09
    FIND
    1.02
    found
    0.94
     found
    0.93
     Found
    0.93
     finds
    0.89
    Activations Density 0.151%

    No Known Activations