© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11915
    Prev
    Next
    INDEX
    Explanations

    mentions of specific numerical values or data attributes

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

    Numbers within parentheses

    np_acts-logits-general · gemini-2.0-flash

    numbers, symbols, and names

    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
    Demonstration
    -0.51
    WireFormatLite
    -0.49
    onAttach
    -0.49
    Tembelea
    -0.48
    inset
    -0.46
     jspb
    -0.46
    getRuntime
    -0.46
     palsy
    -0.45
    ціа
    -0.45
    Previews
    -0.45
    POSITIVE LOGITS
    ')['
    0.76
    Datuak
    0.68
    _
    0.66
    قایناق‌لار
    0.65
    NaN
    0.60
    省市镇
    0.59
    SOUNDBITE
    0.58
    tisgarh
    0.58
    himovic
    0.58
    lorette
    0.58
    Activations Density 0.428%

    No Known Activations