© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 6807
    Prev
    Next
    INDEX
    Explanations

    actions related to movement, particularly ascending or climbing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LabelTagHelper
    -0.63
    Abp
    -0.51
     spot
    -0.50
    phrodite
    -0.49
    Rüyada
    -0.48
     Donat
    -0.47
     Plat
    -0.46
     Kama
    -0.46
    \">\
    -0.46
     PLAT
    -0.46
    POSITIVE LOGITS
     Climbing
    0.97
     ascent
    0.93
     climbing
    0.93
    climbing
    0.93
     climb
    0.92
     verticales
    0.91
     stairs
    0.90
     ladders
    0.87
     Climb
    0.86
     ascending
    0.86
    Activations Density 0.314%

    No Known Activations