© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 237
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the need for improvement or restoration

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

    phrases related to vehicle modifications or enhancements

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

    given a

    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
     AppColors
    -0.81
    rungsseite
    -0.79
    TagMode
    -0.79
    PrototypeOf
    -0.77
    IntoConstraints
    -0.77
     InputDecoration
    -0.75
    BagConstraints
    -0.73
    ThroughAttribute
    -0.73
    )_/¯
    -0.72
    capaian
    -0.71
    POSITIVE LOGITS
     makeover
    0.69
     update
    0.65
     thorough
    0.65
     refresh
    0.63
     TLC
    0.63
     attention
    0.63
     overhaul
    0.58
    update
    0.57
     comprehensive
    0.55
     nudge
    0.54
    Activations Density 0.047%

    No Known Activations