© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5293
    Prev
    Next
    INDEX
    Explanations

    terms related to medical treatment protocols and monitoring

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

    Time intervals or frequencies

    np_acts-logits-general · gemini-2.0-flash

    intervals and frequencies

    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
    Sklici
    -0.66
     للمعارف
    -0.65
     transfieras
    -0.61
    abestanden
    -0.61
     CreateTagHelper
    -0.58
     Vikipedi
    -0.57
    ++];
    -0.56
    書館
    -0.54
    endphp
    -0.53
    佗
    -0.52
    POSITIVE LOGITS
     monthly
    2.43
     weekly
    2.34
     quarterly
    2.23
     annual
    2.19
     yearly
    2.18
    monthly
    2.06
     periodic
    2.05
     annually
    2.03
    weekly
    1.96
     Monthly
    1.89
    Activations Density 0.676%

    No Known Activations