© 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. 3001
    Prev
    Next
    INDEX
    Explanations

    technical or specialized terms related to pharmaceuticals and medical studies

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

    ending in "cept", "iem", "vert" or "/" and numbers

    np_acts-logits-general · gemini-2.0-flash

    aflibercept and conbercept

    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
     Odyssey
    -0.59
     Landis
    -0.57
     Moha
    -0.56
    vav
    -0.55
     Rabin
    -0.55
    א
    -0.54
     Bremer
    -0.54
     Avila
    -0.53
     Parkes
    -0.52
     Shira
    -0.52
    POSITIVE LOGITS
     Osborn
    0.73
     AssemblyTitle
    0.68
     Colbert
    0.67
     Leone
    0.65
     Papi
    0.65
    sene
    0.63
     Baldwin
    0.63
    ItemBackground
    0.63
    Rui
    0.63
     defStyle
    0.63
    Activations Density 0.851%

    No Known Activations