© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6297
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "find" in various contexts, specifically in coding or database queries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    仕方
    -0.38
     verru
    -0.35
     partea
    -0.32
     NotImplemented
    -0.32
    writeValue
    -0.31
     Metzger
    -0.31
    どれだけ
    -0.31
     quantités
    -0.31
     Upgrades
    -0.31
     CONCRETE
    -0.30
    POSITIVE LOGITS
    find
    2.48
    FIND
    1.58
    finding
    1.29
     findings
    1.21
     find
    1.20
     FIND
    1.12
    finds
    1.08
    finder
    1.07
    findAll
    1.06
     finding
    1.01
    Activations Density 0.095%

    No Known Activations