© 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. 3082
    Prev
    Next
    INDEX
    Explanations

    historical events and their significance

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

    preceding "history"

    np_acts-logits-general · gemini-2.0-flash

    specific historical contexts

    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
    nemouth
    -0.52
    yntaxException
    -0.51
    CreateModel
    -0.51
     ISNI
    -0.49
    rouvez
    -0.49
    cluye
    -0.49
    ülerin
    -0.48
     aján
    -0.47
    styleType
    -0.47
    لينكات
    -0.47
    POSITIVE LOGITS
     history
    3.79
    history
    3.27
     History
    3.04
    History
    2.94
     HISTORY
    2.86
    HISTORY
    2.62
     histories
    2.54
     sejarah
    2.44
     historia
    2.39
     historical
    2.33
    Activations Density 0.415%

    No Known Activations