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. 10946
    Prev
    Next
    INDEX
    Explanations

    references to privacy, legal issues, and complaints

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

    Absence or lack of something

    np_acts-logits-general · gemini-2.0-flash

    no registration, no treatment, no comments

    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
    -0.64
    ALREADY
    -0.61
    ynchronously
    -0.61
    もう少し
    -0.58
    ++];
    -0.57
     disambiguazione
    -0.56
     inversely
    -0.53
    correctly
    -0.53
     favourably
    -0.53
    andha
    -0.52
    POSITIVE LOGITS
     whatsoever
    1.42
     nor
    1.02
     no
    0.78
    AndEndTag
    0.75
     alls
    0.74
     except
    0.73
     ไม่มี
    0.69
     nenhuma
    0.67
     aparente
    0.66
    也沒有
    0.65
    Activations Density 0.370%

    No Known Activations