© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 104
    Prev
    Next
    INDEX
    Explanations

    terms related to shifting or adjustments in various contexts

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

    terms related to gear shifting in vehicles

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

    shift and following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    richTextPanel
    -0.65
    ised
    -0.58
     geïsole
    -0.56
    layoutParams
    -0.56
    ""}
    -0.55
    /*"
    -0.54
    artamento
    -0.53
     GoogleFonts
    -0.53
    ğraf
    -0.53
    ganu
    -0.53
    POSITIVE LOGITS
     SHIFT
    0.92
     shifts
    0.91
     shift
    0.89
     Shifts
    0.87
     Shift
    0.86
    hift
    0.86
    shifts
    0.86
     gears
    0.84
    SHIFT
    0.78
    Shift
    0.77
    Activations Density 0.041%

    No Known Activations