© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 9407
    Prev
    Next
    INDEX
    Explanations

    terms related to classification and categorization

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

    ending in "y," "ies," or "ists"

    np_acts-logits-general · gemini-2.0-flash

    word endings like ies, ie, iest, ry, ily, ized

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.59
    Pome
    -0.57
    Slf
    -0.57
     समीक्षक
    -0.56
    WebElementEntity
    -0.54
    ثيق
    -0.53
    Viited
    -0.52
    Obrázky
    -0.52
    niaus
    -0.51
     okuyayım
    -0.51
    POSITIVE LOGITS
    ies
    1.18
    IES
    1.03
     ies
    0.83
    iest
    0.81
    ries
    0.81
    yship
    0.80
    ying
    0.76
    ied
    0.75
    ys
    0.72
    ry
    0.71
    Activations Density 0.275%

    No Known Activations