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. 13881
    Prev
    Next
    INDEX
    Explanations

    HTML table elements and their attributes

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

    HTML table-related tokens

    np_acts-logits-general · gemini-2.0-flash

    DISS dissent, PRRSV interferes

    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
     censure
    -0.46
     censorship
    -0.45
    bilisi
    -0.45
     censor
    -0.42
    enzie
    -0.42
     Cens
    -0.41
    Some
    -0.41
     متعلقه
    -0.40
     
    -0.40
     Chir
    -0.40
    POSITIVE LOGITS
     @"/
    0.78
    ELTS
    0.69
    StreetMap
    0.68
    andExpect
    0.65
    سطس
    0.65
     elif
    0.65
    atric
    0.64
    ंदीखरीदारी
    0.63
    Obrázky
    0.62
    Ђ
    0.62
    Activations Density 0.018%

    No Known Activations