Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1499
    Prev
    Next
    INDEX
    Explanations

    specific scientific and technical measurements or parameters

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

    Numbers within technical contexts

    np_acts-logits-general · gemini-2.0-flash

    hyphenated numbers and units

    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
     satunya
    -0.76
    kmale
    -0.63
     etc
    -0.61
    aaral
    -0.60
    ¹.
    -0.59
    GOTREF
    -0.59
    inheritDoc
    -0.58
    istoitu
    -0.58
    henswürdigkeiten
    -0.58
    ActivityCompat
    -0.56
    POSITIVE LOGITS
    -
    1.61
    -,
    0.93
    ‑
    0.81
    -/
    0.80
    expandindo
    0.73
    -'
    0.73
    -[
    0.72
    -$
    0.71
    -\
    0.71
    -(
    0.70
    Activations Density 0.821%

    No Known Activations