© 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. 11046
    Prev
    Next
    INDEX
    Explanations

    phrases referring to specific types, conditions, or categories

    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
     Grüsse
    -0.57
     hydro
    -0.56
     resourceCulture
    -0.54
    Grüsse
    -0.54
     hydropower
    -0.53
    libatkan
    -0.52
    ohyd
    -0.51
     pagină
    -0.50
    wakili
    -0.50
     hyd
    -0.50
    POSITIVE LOGITS
     certain
    1.54
     Certain
    1.51
    Certain
    1.50
    certain
    1.43
     CERTAIN
    1.27
     certaine
    1.13
     ciertos
    1.08
     ciertas
    1.05
     tertentu
    1.04
     cierto
    1.03
    Activations Density 0.131%

    No Known Activations