Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2224
    Prev
    Next
    INDEX
    Explanations

    CSS transformation functions, particularly those related to rotation and translation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glBegin
    -0.57
    providedIn
    -0.56
    ECL
    -0.53
    bukkit
    -0.53
     ExecuteAsync
    -0.51
     Merle
    -0.49
     Pech
    -0.48
     médicale
    -0.48
    nienie
    -0.48
    eslint
    -0.47
    POSITIVE LOGITS
     rotation
    1.19
     transformations
    1.14
     transformation
    1.10
     rotations
    1.09
    transform
    1.09
     Rotation
    1.08
     translation
    1.07
     transform
    1.06
     rotate
    1.05
     Translation
    1.03
    Activations Density 0.643%

    No Known Activations