© 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. 13548
    Prev
    Next
    INDEX
    Explanations

    the word "such" in various contexts

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

    "such as"

    np_acts-logits-general · gemini-2.0-flash

    such as

    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
    ValueStyle
    -0.68
    RRect
    -0.63
    ništ
    -0.61
    SourceChecksum
    -0.60
    تقاوى
    -0.57
    )++;
    -0.57
    !*\
    -0.55
    basicConfig
    -0.54
    localctx
    -0.54
    ngdoc
    -0.54
    POSITIVE LOGITS
    like
    0.66
     us
    0.57
     ass
    0.54
    ImageContext
    0.51
     cellpadding
    0.51
     those
    0.49
    úgó
    0.49
     Clyde
    0.48
    ondas
    0.48
    those
    0.46
    Activations Density 0.057%

    No Known Activations