© 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. 12992
    Prev
    Next
    INDEX
    Explanations

    descriptors of time-related qualities and intensities

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

    [Adjective] enough

    np_acts-logits-general · gemini-2.0-flash

    adjective/adverb followed by enough

    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
    retum
    -0.59
     AssemblyTitle
    -0.53
    readValue
    -0.52
     ""],
    -0.51
    meteries
    -0.49
    imia
    -0.48
    perma
    -0.48
    copyOf
    -0.48
     former
    -0.46
    <>();
    -0.46
    POSITIVE LOGITS
     enough
    2.75
    enough
    2.39
     Enough
    2.11
    Enough
    2.07
     ENOUGH
    2.06
     genug
    1.97
     genoeg
    1.85
     suficiente
    1.47
     sufficient
    1.36
     demais
    1.34
    Activations Density 0.239%

    No Known Activations