© 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. 10800
    Prev
    Next
    INDEX
    Explanations

    numerical data, particularly sequences and patterns in numbers

    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
     متعلقه
    -1.01
     >=",
    -0.84
     CreateTagHelper
    -0.83
    rrggbb
    -0.80
    NewUrlParser
    -0.79
    DispatchToProps
    -0.74
    पया
    -0.74
    queryInterface
    -0.73
     Garde
    -0.72
     glyphicon
    -0.71
    POSITIVE LOGITS
    xtick
    0.53
    eniendo
    0.52
     Chio
    0.50
    httpMethod
    0.49
    fram
    0.49
    Haw
    0.48
    HWND
    0.46
     Fram
    0.46
     Bartol
    0.46
    DisplayMetrics
    0.45
    Activations Density 0.520%

    No Known Activations