© 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. 11340
    Prev
    Next
    INDEX
    Explanations

    references to specific people or entities, particularly in sports contexts

    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
     braccia
    -1.30
    atoare
    -1.29
     spalle
    -1.17
     gambe
    -1.13
     esfuer
    -1.05
    ătoare
    -1.02
    toarele
    -1.02
     tasche
    -1.01
    toare
    -0.98
     فريبيس
    -0.98
    POSITIVE LOGITS
     meg
    0.60
     az
    0.58
     felt
    0.53
     sz
    0.53
     ny
    0.52
     cs
    0.52
     volt
    0.51
     ker
    0.51
     fel
    0.49
     el
    0.49
    Activations Density 0.031%

    No Known Activations