© 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. 4-GEMMASCOPE-RES-16K
    6. 3784
    Prev
    Next
    INDEX
    Explanations

    numerical and structured data, specifically in formats that denote measurements or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unless
    -0.54
     Einsch
    -0.47
    alo
    -0.44
     b
    -0.44
    tidae
    -0.43
     Hag
    -0.43
    utar
    -0.42
    .
    -0.42
    tm
    -0.41
    unless
    -0.41
    POSITIVE LOGITS
    SequentialGroup
    0.97
    CloseOperation
    0.80
    ynchronously
    0.80
     الدولى
    0.79
     ſtate
    0.78
     BoxDecoration
    0.77
    IsMutable
    0.77
    />";
    0.74
    photobucket
    0.74
    AddHtmlAttribute
    0.73
    Activations Density 0.347%

    No Known Activations