© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8366
    Prev
    Next
    INDEX
    Explanations

    terms related to geospatial analysis and neoantigen research

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

    Prefixes: geo, neo, homo, eo, ko, xo

    np_acts-logits-general · gemini-2.0-flash

    geo, neo, homo, iso prefixes

    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
    是
    -0.76
    に
    -0.68
    y
    -0.67
    bbene
    -0.61
     تضيفلها
    -0.60
    fully
    -0.56
    p
    -0.55
    ActionButton
    -0.53
    ۰
    -0.53
    pla
    -0.53
    POSITIVE LOGITS
    й
    0.63
    beispiel
    0.58
    pezi
    0.54
     UnityEditor
    0.52
    gemeente
    0.52
    intersection
    0.51
     فريبيس
    0.51
    flüs
    0.51
    shore
    0.50
     Salva
    0.48
    Activations Density 0.309%

    No Known Activations