© 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. 24-GEMMASCOPE-RES-16K
    6. 2524
    Prev
    Next
    INDEX
    Explanations

    technical terminology and operations related to data manipulation and analysis in Python, specifically focusing on multi-dimensional array processing and calculations

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

    Code, numbers, or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    array indexing notation

    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
    PerformLayout
    -0.58
    SourceChecksum
    -0.57
    )="
    -0.53
     EXECUTIVE
    -0.50
    BaseAdapter
    -0.50
     exec
    -0.50
     Executive
    -0.49
     Ste
    -0.48
    ]="
    -0.48
     next
    -0.48
    POSITIVE LOGITS
    [:,
    1.13
    [...,
    0.68
    [:,:,
    0.68
    [[
    0.68
    [:
    0.66
    [
    0.64
    
    0.59
     @
    0.59
     [@
    0.58
    (:,
    0.58
    Activations Density 0.061%

    No Known Activations