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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 78166
    Prev
    Next
    INDEX
    Explanations

    terms related to torque specifications and measurements in vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    engine torque and Nm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ambién
    -0.45
    Identyfik
    -0.42
     JFrame
    -0.40
    chb
    -0.40
     פני
    -0.40
    selig
    -0.39
     télévis
    -0.38
     uden
    -0.37
     évi
    -0.37
     allAfrica
    -0.36
    POSITIVE LOGITS
     Nm
    0.88
    Nm
    0.82
     torque
    0.70
    torque
    0.62
    Torque
    0.62
     Torque
    0.59
     torsion
    0.58
    featureID
    0.55
    rungsseite
    0.50
     moment
    0.50
    Activations Density 0.028%

    No Known Activations