© 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. 16-GEMMASCOPE-RES-16K
    11. 14753
    Prev
    Next
    INDEX
    Explanations

    references to technical specifications or data formats

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

    Hexadecimal strings in URLs or file paths

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal strings and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -0.78
     AssemblyCulture
    -0.78
    GEBURTSDATUM
    -0.78
    @[+][
    -0.78
     nakalista
    -0.74
    发表于
    -0.71
     wireType
    -0.70
     ویکی‌پدی
    -0.68
    الإنجليزية
    -0.68
    DotNetBar
    -0.66
    POSITIVE LOGITS
     Gea
    0.52
     setData
    0.49
    Eacute
    0.49
     Villiers
    0.48
    に出て
    0.48
    ulary
    0.46
    exponential
    0.45
     Gland
    0.45
    ığında
    0.45
     Buddy
    0.44
    Activations Density 0.174%

    No Known Activations