© 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. 12-GEMMASCOPE-RES-16K
    11. 2983
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of picking up or lifting objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wirth
    -0.50
     VIAF
    -0.50
    ||}
    -0.49
     Hartman
    -0.48
     réus
    -0.48
     Schulte
    -0.48
     Hartmann
    -0.46
    htä
    -0.46
     ZONE
    -0.46
     Zone
    -0.44
    POSITIVE LOGITS
    Pick
    1.34
     pick
    1.33
     Pick
    1.31
     Pickup
    1.27
    pick
    1.27
     pickup
    1.23
    PICK
    1.22
     PICK
    1.21
    Pickup
    1.18
     picked
    1.17
    Activations Density 0.087%

    No Known Activations