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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 1531
    Prev
    Next
    INDEX
    Explanations

    references to software and technical terms related to 3D modeling and animation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVEREF
    -0.57
     kaarangay
    -0.55
     Houghton
    -0.52
     Munt
    -0.51
    Heb
    -0.49
     Fenn
    -0.48
    hank
    -0.48
     Bok
    -0.48
    rom
    -0.48
     Dube
    -0.47
    POSITIVE LOGITS
     Blender
    1.03
     render
    0.90
     Maya
    0.87
     blender
    0.86
     renders
    0.84
     Render
    0.83
    Blender
    0.82
     maya
    0.80
    Maya
    0.78
     sculpting
    0.77
    Activations Density 0.258%

    No Known Activations