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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 13176
    Prev
    Next
    INDEX
    Explanations

    references to different types of flooring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newVal
    -0.79
     Ives
    -0.75
    多い
    -0.75
     acte
    -0.74
     Königreich
    -0.72
    acana
    -0.71
    pidou
    -0.70
    เป
    -0.70
     sauvage
    -0.70
    sgn
    -0.69
    POSITIVE LOGITS
     floors
    1.51
     Floor
    1.49
     floor
    1.48
     FLOOR
    1.42
     Floors
    1.38
    FLOOR
    1.36
    Floor
    1.35
    floors
    1.33
    floor
    1.32
     flooring
    1.15
    Activations Density 0.033%

    No Known Activations