© 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. 10856
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Sav" and its variations

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

    "Sav" followed by a vowel

    np_acts-logits-general · gemini-2.0-flash

    savoury, savour, saville, savable, savvier, saviors

    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
     resourceCulture
    -0.58
    AlterField
    -0.52
    twimg
    -0.48
    joi
    -0.46
    GroupLayout
    -0.46
     Bourgoin
    -0.46
    e
    -0.45
     Innes
    -0.45
    getExternal
    -0.45
     where
    -0.43
    POSITIVE LOGITS
    EndContext
    0.71
     houſe
    0.66
    yntaxException
    0.66
     שוליים
    0.66
     LoggerFactory
    0.66
     Jefus
    0.65
     ſhall
    0.61
    InitVars
    0.57
     sánchez
    0.57
     bershka
    0.57
    Activations Density 0.160%

    No Known Activations