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. 20-GEMMASCOPE-RES-16K
    6. 15576
    Prev
    Next
    INDEX
    Explanations

    tokens related to the term "Sk" and its variations, likely indicating a focus on different types of skies or other similar terms

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

    starting with "Sk"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Sk

    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
     مشين
    -0.80
    localctx
    -0.63
    djangoproject
    -0.59
    /*
    -0.56
    )++;
    -0.55
    AddTagHelper
    -0.54
     endwhile
    -0.53
    InlineData
    -0.53
    irot
    -0.52
    multicolumn
    -0.52
    POSITIVE LOGITS
     Sk
    0.83
    Sk
    0.80
     sk
    0.79
     Skelton
    0.71
     SK
    0.70
     Skid
    0.68
    Esk
    0.63
    Sku
    0.57
    SK
    0.57
     Skrill
    0.57
    Activations Density 0.093%

    No Known Activations