© 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-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4733
    Prev
    Next
    INDEX
    Explanations

    instances of the word "jump" and its variations, indicating a focus on jumping actions or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.71
     дописавши
    -0.65
    الحياه
    -0.62
     NSCoder
    -0.60
     étrangères
    -0.57
    oneofs
    -0.57
    Datuak
    -0.56
    GeneratedCode
    -0.54
    HomeAsUpEnabled
    -0.54
    ModelState
    -0.53
    POSITIVE LOGITS
     jump
    3.89
     Jump
    3.63
    jump
    3.51
    Jump
    3.39
     jumps
    3.38
     JUMP
    3.33
     jumping
    3.23
     jumped
    3.21
     Jumping
    2.90
    jumping
    2.87
    Activations Density 0.035%

    No Known Activations