© 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-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 10632
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate proof, demonstration, or evidence in research-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -0.78
    Portail
    -0.74
     Мексичка
    -0.70
     beſch
    -0.69
     ſein
    -0.66
     geſch
    -0.65
     $_"
    -0.65
     Geſch
    -0.65
     erſt
    -0.64
     ſeine
    -0.63
    POSITIVE LOGITS
     also
    0.41
     seen
    0.33
     sabido
    0.33
     that
    0.32
     samtidig
    0.32
     siir
    0.30
    有一个
    0.30
     Also
    0.29
     ό
    0.29
     samtidigt
    0.29
    Activations Density 2.177%

    No Known Activations