© 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. 10673
    Prev
    Next
    INDEX
    Explanations

    keywords related to location and geography in a context involving hospitals and educational institutions

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

    Text after specific prepositions or within parentheses

    np_acts-logits-general · gemini-2.0-flash

    prepositions before names

    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
     AssemblyTitle
    -0.70
    IntoConstraints
    -0.70
     @"/
    -0.69
     saites
    -0.66
     חיצוניים
    -0.66
     auffi
    -0.64
     Sardin
    -0.63
     BoxFit
    -0.61
     Florentine
    -0.61
    PreExecute
    -0.60
    POSITIVE LOGITS
     dAtA
    0.54
    曖昧さ回避
    0.53
    ervlak
    0.52
    quiao
    0.51
    lapsingToolbar
    0.49
    atrician
    0.49
    olute
    0.48
     بیر
    0.48
    IsRequired
    0.46
    TableAdapter
    0.46
    Activations Density 0.200%

    No Known Activations