© 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 - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6899
    Prev
    Next
    INDEX
    Explanations

    references to "Hall of Fame" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Devine
    -0.69
     Nib
    -0.68
     bê
    -0.68
     myſelf
    -0.66
    Beste
    -0.66
     Stokes
    -0.66
     Biele
    -0.65
     sê
    -0.64
    économie
    -0.64
     reactive
    -0.63
    POSITIVE LOGITS
     hall
    3.31
     Hall
    3.27
     HALL
    3.08
    Hall
    3.03
     halls
    2.78
    hall
    2.76
    HALL
    2.61
     Halls
    2.54
     hallway
    1.77
     hallways
    1.47
    Activations Density 0.030%

    No Known Activations