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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13-GEMMASCOPE-RES-16K
    6. 12344
    Prev
    Next
    INDEX
    Explanations

    instances of the word "seek" and its variations, indicating a search for permission or approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MemoryWarning
    -0.85
    mappedBy
    -0.75
     McDon
    -0.73
    ftagPool
    -0.72
    ViewFeatures
    -0.70
     dud
    -0.70
    OGND
    -0.70
    ConstraintMaker
    -0.69
    Gras
    -0.66
    mybatisplus
    -0.66
    POSITIVE LOGITS
     seek
    1.53
     Seeking
    1.50
     Seek
    1.43
     seeks
    1.43
     SEEK
    1.43
     seeking
    1.42
     sought
    1.32
    seeking
    1.29
    Seek
    1.25
    seek
    1.24
    Activations Density 0.056%

    No Known Activations