© 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. 1-GEMMASCOPE-RES-16K
    11. 4184
    Prev
    Next
    INDEX
    Explanations

    references to "torque" and related terms in the context of physical phenomena, particularly in relation to neutron stars

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sahabat
    -0.42
    ChildScrollView
    -0.39
     Cotter
    -0.39
    ̈́
    -0.37
     Hodg
    -0.36
     estimés
    -0.35
     blogger
    -0.34
    farwyddwr
    -0.34
    edoria
    -0.34
    在哪
    -0.33
    POSITIVE LOGITS
    EF
    0.75
     tor
    0.75
    ef
    0.68
    tor
    0.66
     Tor
    0.64
    Sense
    0.63
    Tor
    0.61
     torch
    0.61
    sense
    0.59
    oring
    0.59
    Activations Density 0.287%

    No Known Activations