© 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. 8149
    Prev
    Next
    INDEX
    Explanations

    references to government, cooperation, and active participation in collaborative efforts

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

    increased efforts or intentions

    np_acts-logits-general · gemini-2.0-flash

    auxiliary verbs followed by main verbs

    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
    sizeCache
    -0.56
    MarshalTo
    -0.53
     muttered
    -0.52
     PLWABN
    -0.52
    Witam
    -0.52
    ThemeOverlay
    -0.48
    momix
    -0.48
     estekak
    -0.47
     loves
    -0.47
     referencing
    -0.47
    POSITIVE LOGITS
     actively
    0.85
     intensify
    0.84
     intensi
    0.83
     intensified
    0.78
     continuously
    0.74
     aggressively
    0.72
     efforts
    0.71
     regularly
    0.69
     vigorously
    0.69
     Efforts
    0.68
    Activations Density 0.187%

    No Known Activations