© 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. 5714
    Prev
    Next
    INDEX
    Explanations

    function declarations and method calls in programming code

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

    Code snippets with time or date functions

    np_acts-logits-general · gemini-2.0-flash

    milliseconds or time durations

    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
     catch
    -1.53
     catching
    -1.46
     Catch
    -1.38
     caught
    -1.32
     catches
    -1.31
    catch
    -1.26
    caught
    -1.20
     CATCH
    -1.20
    catching
    -1.18
     Caught
    -1.17
    POSITIVE LOGITS
    Durée
    0.47
     kasarigan
    0.45
     senhor
    0.43
     Dostupné
    0.43
     endregion
    0.43
     ms
    0.43
     Executive
    0.42
     governador
    0.41
    Pfalz
    0.41
    aryen
    0.40
    Activations Density 0.109%

    No Known Activations