© 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. 11475
    Prev
    Next
    INDEX
    Explanations

    actions and processes related to gravity and dropping 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
    ſelves
    -0.55
    setVerticalGroup
    -0.52
     ſaid
    -0.51
     Reſ
    -0.50
     AssemblyCompany
    -0.50
    الحياه
    -0.50
    +#+
    -0.49
     myſelf
    -0.49
    rekli
    -0.49
     Inſ
    -0.49
    POSITIVE LOGITS
     dropping
    0.74
     falling
    0.74
     down
    0.73
     fall
    0.73
    Falling
    0.72
     downward
    0.69
     Falling
    0.67
     Fall
    0.66
     drop
    0.66
     descent
    0.66
    Activations Density 0.614%

    No Known Activations