© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6459
    Prev
    Next
    INDEX
    Explanations

    instances of the word "seek" and its variations, indicating a focus on searching or searching out something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    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
    -0.80
     dud
    -0.73
     Compli
    -0.68
    ズミ
    -0.67
     everybody
    -0.66
    Everybody
    -0.64
    ftagPool
    -0.64
    boys
    -0.64
     McCon
    -0.62
    XtraEditors
    -0.62
    POSITIVE LOGITS
     seek
    2.25
     Seek
    2.17
     Seeking
    2.12
     seeking
    2.12
     seeks
    2.08
     SEEK
    2.02
    seeking
    1.95
    Seek
    1.93
    seek
    1.92
    Seeking
    1.91
    Activations Density 0.074%

    No Known Activations