© 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. 13054
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare delivery and intervention evaluations

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

    frequency or typicality

    np_acts-logits-general · gemini-2.0-flash

    usually often typically

    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
     AssemblyCulture
    -0.61
     متعلقه
    -0.54
     SqlDbType
    -0.54
     cherchés
    -0.49
    reathable
    -0.49
    AddAttribute
    -0.48
    このまま
    -0.47
    haupt
    -0.47
    pragma
    -0.47
    '}}>
    -0.47
    POSITIVE LOGITS
     usually
    3.53
     often
    3.30
    usually
    3.14
     typically
    3.08
     Usually
    3.05
    Usually
    3.04
     Often
    2.94
    often
    2.88
    Often
    2.86
    typically
    2.74
    Activations Density 2.542%

    No Known Activations