© 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. 8212
    Prev
    Next
    INDEX
    Explanations

    references to algorithms and programming concepts

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

    following "Eg" or similar two-letter sequences

    np_acts-logits-general · gemini-2.0-flash

    eg / Arg / Leg / Berg + common suffixes

    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
    oma
    -0.66
    webElementXpaths
    -0.64
    surfaces
    -0.64
    oss
    -0.58
    er
    -0.57
    ova
    -0.57
    ovski
    -0.56
    uta
    -0.55
     better
    -0.54
    Pax
    -0.54
    POSITIVE LOGITS
    standers
    0.55
    hemiah
    0.51
    didSet
    0.50
     craindre
    0.50
    最快更新
    0.47
     perju
    0.47
     useHistory
    0.46
    WriteLiteral
    0.46
     ujednoznacz
    0.45
    Extinguishing
    0.45
    Activations Density 0.266%

    No Known Activations