© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 6849
    Prev
    Next
    INDEX
    Explanations

    phrases related to "arc" shapes and "Golden" terms in contexts such as sports or geometry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.66
    MessageOf
    -0.62
     ProtoMessage
    -0.60
    nbar
    -0.57
    drawal
    -0.57
    hematical
    -0.57
    Emails
    -0.57
    amemnon
    -0.57
     damages
    -0.56
    ANIUM
    -0.56
    POSITIVE LOGITS
    trajectory
    0.41
     gesture
    0.39
     mentor
    0.39
    Gesture
    0.38
     trajectory
    0.38
    Acts
    0.34
     gest
    0.33
    Personensuche
    0.33
    (((
    0.33
    gesture
    0.32
    Activations Density 0.204%

    No Known Activations