© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12328
    Prev
    Next
    INDEX
    Explanations

    numerical representations or values

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

    Directional words: "left" or "right"

    np_acts-logits-general · gemini-2.0-flash

    left and right movement

    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
    UnitTesting
    -0.56
    іод
    -0.49
    tagext
    -0.49
     становника
    -0.46
    jstor
    -0.45
    ValueGeneration
    -0.43
     onCancelled
    -0.43
    </caption>
    -0.42
    ArgumentParser
    -0.42
     comuniques
    -0.41
    POSITIVE LOGITS
     left
    3.22
    left
    2.69
     Left
    2.68
     right
    2.60
    Left
    2.59
     LEFT
    2.48
    right
    2.35
     Right
    2.32
    LEFT
    2.29
    Right
    2.26
    Activations Density 0.695%

    No Known Activations