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. 9366
    Prev
    Next
    INDEX
    Explanations

    the name "Tan" in various contexts

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

    starting with "Tan" or "tan"

    np_acts-logits-general · gemini-2.0-flash

    Tan followed by it, et, or tamount

    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
    IContainer
    -0.70
    Havolalar
    -0.69
     kasarigan
    -0.68
     whoſe
    -0.67
     >=",
    -0.66
    $}}
    -0.66
     estekak
    -0.66
    )="
    -0.65
    ölkerung
    -0.65
    <>();
    
    -0.63
    POSITIVE LOGITS
     tan
    0.61
     Tan
    0.60
    Tan
    0.60
    tan
    0.58
    trums
    0.51
     TAN
    0.48
     möjligt
    0.47
    čním
    0.46
    tamount
    0.45
    Tē
    0.44
    Activations Density 0.090%

    No Known Activations