© 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. 8218
    Prev
    Next
    INDEX
    Explanations

    conjunctions and expressions indicating contrast or comparison in sentences

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

    Sentences beginning with "I" or "but"

    np_acts-logits-general · gemini-2.0-flash

    but I

    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
     zwar
    -0.89
     sice
    -0.76
     übrigens
    -0.75
    évaluateur
    -0.70
     mergeFrom
    -0.70
    makeConstraints
    -0.69
     оригіналу
    -0.69
     even
    -0.67
     além
    -0.66
     كومونز
    -0.66
    POSITIVE LOGITS
     nonetheless
    2.03
     nevertheless
    1.95
     dennoch
    1.38
     ändå
    1.30
     trotzdem
    1.27
    それでも
    1.25
    Nonetheless
    1.25
     néanmoins
    1.21
    Nevertheless
    1.20
     Nonetheless
    1.16
    Activations Density 0.405%

    No Known Activations