© 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. 3-GEMMASCOPE-RES-16K
    6. 5394
    Prev
    Next
    INDEX
    Explanations

    labels or identifiers used in a structured list or selection format, particularly related to options or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ||=
    -0.63
     Persson
    -0.60
    ]+=
    -0.56
    industan
    -0.56
    ="{{$
    -0.55
    Autoritní
    -0.54
     {{$
    -0.52
    ὖ
    -0.51
    < 
    -0.51
    المراجع
    -0.50
    POSITIVE LOGITS
     Baillargeon
    0.77
     lenker
    0.65
     Pries
    0.64
    b
    0.63
    WebServlet
    0.62
    a
    0.59
    ii
    0.58
     jsPsych
    0.57
    例文帳に追加
    0.57
    glEnd
    0.56
    Activations Density 0.313%

    No Known Activations