© 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. 7716
    Prev
    Next
    INDEX
    Explanations

    phrases related to responsibilities and competencies in a healthcare or educational context

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

    Punctuation, symbols, and conjunctions

    np_acts-logits-general · gemini-2.0-flash

    action, ability, or state

    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
     Dummies
    -0.52
    openSession
    -0.52
    alamus
    -0.48
    execSQL
    -0.48
     ProtoMessage
    -0.48
    FXMLLoader
    -0.47
     schauen
    -0.46
    ってしまった
    -0.45
    Кстати
    -0.45
    Voci
    -0.44
    POSITIVE LOGITS
    #+#
    0.80
     disambiguazione
    0.73
     contextLoads
    0.71
     calendriers
    0.69
    RetentionPolicy
    0.67
     otomatig
    0.67
    Demon
    0.66
    
    0.66
    Personensuche
    0.64
     שוליים
    0.63
    Activations Density 0.181%

    No Known Activations