© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 7593
    Prev
    Next
    INDEX
    Explanations

    physical interactions and descriptions involving body parts and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.63
     Wrist
    -0.61
     Neck
    -0.55
     wrist
    -0.52
    Wrist
    -0.52
     Foot
    -0.52
     Hand
    -0.52
     Ankle
    -0.51
    IsMutable
    -0.51
    HtmlAttribute
    -0.50
    POSITIVE LOGITS
     hands
    0.99
     arms
    0.79
     legs
    0.69
     heads
    0.68
     paws
    0.65
     knees
    0.65
     feet
    0.64
     eyes
    0.60
    Autoritní
    0.60
     backs
    0.59
    Activations Density 0.529%

    No Known Activations