© 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. 7728
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features related to software and hardware products

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

    "pre" or prefixes

    np_acts-logits-general · gemini-2.0-flash

    predefined

    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
     OFDb
    -0.74
     Roskov
    -0.66
    rawDesc
    -0.66
    новниш
    -0.64
     мәкалә
    -0.63
     препратки
    -0.62
     Paglinawan
    -0.60
    useNewUrlParser
    -0.56
    CodedInputStream
    -0.56
    tagHelperRunner
    -0.55
    POSITIVE LOGITS
     pre
    2.22
    pre
    1.76
     predefined
    1.74
     ready
    1.67
     Pre
    1.63
    Pre
    1.62
     preset
    1.57
     pré
    1.54
     гото
    1.46
    ready
    1.45
    Activations Density 0.524%

    No Known Activations