© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10047
    Prev
    Next
    INDEX
    Explanations

    words indicating awe and admiration

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

    Begins with "Gro" or "aw"

    np_acts-logits-general · gemini-2.0-flash

    Grozny, awesomeness, AWANA

    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
    ={({
    -0.49
    laşı
    -0.45
    laston
    -0.44
    baomidou
    -0.43
    gak
    -0.41
    Swish
    -0.40
     antidesliz
    -0.40
    ORAGE
    -0.40
    quef
    -0.40
     particularmente
    -0.39
    POSITIVE LOGITS
    sizeCache
    1.00
    IsMutable
    0.99
    +#+
    0.91
     tartalomajánló
    0.83
    رشف
    0.83
     ویکی‌پدی
    0.82
     للاسماء
    0.81
     Wikimedijinoj
    0.80
    Tikang
    0.78
     BoxDecoration
    0.73
    Activations Density 0.363%

    No Known Activations