© 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. 3-GEMMASCOPE-RES-16K
    11. 8549
    Prev
    Next
    INDEX
    Explanations

    terms related to rotational mechanics and movements in machinery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inter
    -0.52
    mun
    -0.46
    cuito
    -0.44
     et
    -0.44
     
    -0.42
    patch
    -0.42
     imp
    -0.42
     patch
    -0.42
     em
    -0.42
    ophy
    -0.41
    POSITIVE LOGITS
     rotate
    1.11
     rotates
    1.10
     Rotate
    1.09
     rotating
    1.03
     Rotating
    1.01
     swing
    1.00
    Rotating
    0.99
     swings
    0.98
     rotated
    0.97
    rotated
    0.97
    Activations Density 0.814%

    No Known Activations