© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 929
    Prev
    Next
    INDEX
    Explanations

    references to physical activity and exercise preferences in children and their parents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.52
     ujednoznacz
    -0.51
    kwür
    -0.50
     ProtoMessage
    -0.49
     protoimpl
    -0.47
    Tracce
    -0.47
    Personendaten
    -0.46
    CodeAttribute
    -0.45
     générations
    -0.44
    InjectAttribute
    -0.43
    POSITIVE LOGITS
     workout
    1.11
     fitness
    1.09
     gym
    1.06
     workouts
    1.02
    Fitness
    0.99
    fitness
    0.98
     Fitness
    0.97
     exercise
    0.96
     gyms
    0.93
    gym
    0.90
    Activations Density 0.307%

    No Known Activations