© 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. 8967
    Prev
    Next
    INDEX
    Explanations

    references to significant individuals and events in history and literature

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

    after capitalized words/names

    np_acts-logits-general · gemini-2.0-flash

    famous surnames and the start of 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
     quæ
    -1.31
     ſtand
    -1.29
     Efq
    -1.28
     reaſon
    -1.26
     purpoſe
    -1.23
     ſeveral
    -1.20
     myſelf
    -1.19
     ſtate
    -1.17
     cauſe
    -1.16
     anſ
    -1.14
    POSITIVE LOGITS
      
    0.43
    ˈ
    0.42
    abestanden
    0.41
     melang
    0.39
    <eos>
    0.39
    bootstrapcdn
    0.38
    あたり
    0.37
    的影响
    0.36
    寸
    0.36
     satte
    0.35
    Activations Density 1.152%

    No Known Activations