© 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. 35-GEMMASCOPE-RES-16K
    11. 11351
    Prev
    Next
    INDEX
    Explanations

    references to football (soccer) players and their actions during a match

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     @"/
    -0.51
     مشين
    -0.51
    SceneManagement
    -0.48
     InputDecoration
    -0.48
    MarshalTo
    -0.47
     تكبرها
    -0.47
    msgTypes
    -0.46
    AutoScaleMode
    -0.45
     MainAxisSize
    -0.44
    CloseOperation
    -0.43
    POSITIVE LOGITS
     curling
    0.48
     penalty
    0.46
     header
    0.46
     curled
    0.44
     effort
    0.42
     volley
    0.42
     efforts
    0.42
     cross
    0.41
     headed
    0.40
     crosses
    0.40
    Activations Density 0.155%

    No Known Activations