Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2887
    Prev
    Next
    INDEX
    Explanations

    words associated with walking or movement activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toiminta
    -0.45
     misiones
    -0.44
    Voltaje
    -0.39
     piracy
    -0.38
     verhalen
    -0.37
     gründ
    -0.35
     excursions
    -0.34
     sequencing
    -0.34
    zanas
    -0.33
     verità
    -0.33
    POSITIVE LOGITS
     sitting
    1.55
     standing
    1.48
     walking
    1.39
    Sitting
    1.30
    sitting
    1.28
     Sitting
    1.27
     Standing
    1.23
     Walking
    1.23
    Standing
    1.20
    walking
    1.13
    Activations Density 0.232%

    No Known Activations