© 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. 10204
    Prev
    Next
    INDEX
    Explanations

    instances where something operates smoothly or effectively

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

    "[something] works [adverb]"

    np_acts-logits-general · gemini-2.0-flash

    just works fine

    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
    ISupport
    -0.78
     Eſ
    -0.73
     ſtate
    -0.73
     leaſt
    -0.72
    Geplaatst
    -0.71
     myſelf
    -0.71
     fubject
    -0.65
    GEBURTS
    -0.65
     themſelves
    -0.65
     purpoſe
    -0.64
    POSITIVE LOGITS
     dandy
    0.92
     fine
    0.88
     great
    0.75
     beaut
    0.74
     grand
    0.71
     swell
    0.69
     lovely
    0.66
     charm
    0.64
     sweet
    0.62
    great
    0.61
    Activations Density 0.163%

    No Known Activations