© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 14731
    Prev
    Next
    INDEX
    Explanations

    references to healthcare facilities and medical staff

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

    following "of," "by," "at," "in," "uses," or "using."

    np_acts-logits-general · gemini-2.0-flash

    institutional or geographical names

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Purdue
    -0.50
     Chicago
    -0.46
     CHICAGO
    -0.44
     Miami
    -0.43
     Corning
    -0.43
     pist
    -0.42
     Marseille
    -0.42
     Франции
    -0.42
    Purdue
    -0.41
     Hanford
    -0.41
    POSITIVE LOGITS
     صوتيه
    1.09
    KURZBESCHREIBUNG
    0.92
    PerformLayout
    0.92
    LookAnd
    0.91
    HasForeignKey
    0.88
    styleType
    0.87
    (!__
    0.85
     EconPapers
    0.83
    
    0.82
    UnusedPrivate
    0.82
    Activations Density 0.175%

    No Known Activations