© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 14947
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly those beginning with "Al."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createSprite
    -0.83
     وتسجيلات
    -0.80
     Huguen
    -0.77
    Dữ
    -0.76
     noastră
    -0.75
     resign
    -0.73
     Réponses
    -0.73
    ensity
    -0.71
     Creme
    -0.71
     Dü
    -0.70
    POSITIVE LOGITS
     Al
    1.27
     AL
    1.26
    Al
    1.15
     Alley
    1.10
     al
    1.02
     Alu
    1.01
     Albrecht
    1.01
    Alu
    1.01
     Albright
    0.97
    AL
    0.95
    Activations Density 0.312%

    No Known Activations