© 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. 3496
    Prev
    Next
    INDEX
    Explanations

    conjunctions and linking words that connect phrases or ideas

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

    Tokens appearing before "and" or "or"

    np_acts-logits-general · gemini-2.0-flash

    and followed by a word

    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
     E
    -0.90
    E
    -0.89
     э
    -0.87
    Email
    -0.85
     email
    -0.84
     É
    -0.82
     epithelial
    -0.81
     Email
    -0.79
    epsilon
    -0.78
     EP
    -0.78
    POSITIVE LOGITS
     saites
    0.61
     referenties
    0.48
    nsito
    0.46
    +};
    0.44
    mergeFrom
    0.44
     disambiguazione
    0.43
    󠁴
    0.43
    قایناق‌لار
    0.42
     ſta
    0.42
    ISCO
    0.42
    Activations Density 0.512%

    No Known Activations