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. 20-GEMMASCOPE-RES-16K
    6. 6665
    Prev
    Next
    INDEX
    Explanations

    interests and discussions related to expertise and participation in specific fields

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

    "interest" or "interested"

    np_acts-logits-general · gemini-2.0-flash

    interest and interest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    HtmlAttribute
    -0.55
     honte
    -0.53
    ---+
    -0.53
    ůvod
    -0.52
     AssemblyCulture
    -0.51
     Evidence
    -0.50
     LUMP
    -0.49
    hella
    -0.49
    IBU
    -0.48
    Glück
    -0.47
    POSITIVE LOGITS
     interest
    2.76
    interest
    2.39
     INTEREST
    2.35
     Interest
    2.30
    Interest
    2.21
     interests
    2.21
     interested
    2.14
    INTEREST
    2.14
     interes
    1.96
    interested
    1.88
    Activations Density 0.363%

    No Known Activations