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. 12355
    Prev
    Next
    INDEX
    Explanations

    keywords that signify current relevance or status in a discussion

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

    "...at least" qualifier

    np_acts-logits-general · gemini-2.0-flash

    at least

    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
     imageNamed
    -0.66
     كومونز
    -0.62
    참고
    -0.52
    ագրություններ
    -0.49
     बताया
    -0.47
    eaked
    -0.47
    jestel
    -0.47
    apimachinery
    -0.47
     муніципалі
    -0.47
    往
    -0.47
    POSITIVE LOGITS
     atleast
    2.81
     almeno
    2.52
     zumindest
    2.38
    至少
    2.35
     wenigstens
    2.30
     setidaknya
    2.19
    少なくとも
    2.05
    起码
    1.87
     حداقل
    1.85
     least
    1.84
    Activations Density 0.412%

    No Known Activations