© 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. 22-GEMMASCOPE-RES-16K
    11. 13138
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and expressions related to functions and their properties

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

    Mathematical or scientific notation indices (k, n, i)

    np_acts-logits-general · gemini-2.0-flash

    mathematical indexing and equality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.80
    KommentareTeilen
    -0.78
     estekak
    -0.76
     Normdatei
    -0.76
    tagHelperRunner
    -0.75
    MigrationBuilder
    -0.73
     contextLoads
    -0.72
    ########.
    -0.72
    曖昧さ回避
    -0.71
    agissait
    -0.68
    POSITIVE LOGITS
    =
    0.44
    substack
    0.41
    meren
    0.41
     limitado
    0.40
    thèse
    0.40
     centrales
    0.40
     formules
    0.39
    ears
    0.39
    legend
    0.38
     féminine
    0.38
    Activations Density 0.760%

    No Known Activations