© 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. 21-GEMMASCOPE-RES-16K
    11. 3292
    Prev
    Next
    INDEX
    Explanations

    phrases indicating variety and breadth in offerings or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.81
    хьтан
    -0.73
    GEBURTSDATUM
    -0.68
    GOTREF
    -0.67
    AsUp
    -0.66
     AssemblyTitle
    -0.63
    MigrationBuilder
    -0.61
    contentLoaded
    -0.59
     ब्रेकडाउन
    -0.58
     חיצוניים
    -0.58
    POSITIVE LOGITS
     range
    1.10
     wide
    0.91
     variety
    0.88
    range
    0.77
     array
    0.72
     RANGE
    0.69
     Range
    0.69
    Range
    0.68
     broad
    0.67
     Wide
    0.66
    Activations Density 0.155%

    No Known Activations