© 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. 5382
    Prev
    Next
    INDEX
    Explanations

    terms related to archaeological findings and materials

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

    Archaeological findings and periods

    np_acts-logits-general · gemini-2.0-flash

    ancient archaeological artifacts

    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
    SuppressLint
    -0.64
     Conservatory
    -0.61
     Elast
    -0.61
    Fil
    -0.59
     Hered
    -0.55
     miliardi
    -0.55
     autorisés
    -0.55
     Filtration
    -0.53
     Waldorf
    -0.53
    SupportActionBar
    -0.53
    POSITIVE LOGITS
     archaeological
    0.76
    Archae
    0.66
     Late
    0.66
    FunctionFlags
    0.63
     Neolithic
    0.62
    Late
    0.62
     Archaeological
    0.60
     prehistoric
    0.60
     archaeologists
    0.57
    gnac
    0.56
    Activations Density 0.312%

    No Known Activations