© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 22-GEMMASCOPE-RES-16K
    11. 6541
    Prev
    Next
    INDEX
    Explanations

    dynamic action verbs related to performing complex physical maneuvers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Gymnastics, stunts, and physical feats

    np_acts-logits-general · gemini-2.0-flash

    athletic actions and stunts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ApiModelProperty
    -0.58
    MLLoader
    -0.51
     Económica
    -0.51
     يتيمه
    -0.49
    看不
    -0.49
     Umum
    -0.48
    MPa
    -0.47
     humeur
    -0.47
    mnar
    -0.46
    denza
    -0.46
    POSITIVE LOGITS
     jump
    0.77
     jumps
    0.74
     reverse
    0.72
     jumping
    0.71
     salto
    0.71
     Reverse
    0.70
     backwards
    0.69
     double
    0.68
     inverted
    0.68
     backward
    0.67
    Activations Density 0.296%

    No Known Activations