© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 7336
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names, particularly those beginning with "Ro" and "Mo."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amitié
    -0.32
    enderal
    -0.32
    mi
    -0.32
    astanza
    -0.31
     Cambio
    -0.30
    esterno
    -0.29
     świ
    -0.29
    Background
    -0.29
    so
    -0.28
     aguda
    -0.28
    POSITIVE LOGITS
     MessageBoxIcon
    0.60
     purpoſe
    0.59
    pportun
    0.56
     MainAxisSize
    0.56
     ſch
    0.56
    LayoutPanel
    0.55
     doInBackground
    0.55
     houſe
    0.54
    arangay
    0.54
     ſche
    0.54
    Activations Density 0.307%

    No Known Activations