© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5611
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to electrical systems and control mechanisms

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

    Motor speed and control systems

    np_acts-logits-general · gemini-2.0-flash

    speed control feedback

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    korn
    -0.43
    RUnlock
    -0.43
     Abi
    -0.43
     findViewById
    -0.42
     acceptez
    -0.42
     ску
    -0.42
     crunch
    -0.41
    enumii
    -0.41
    thood
    -0.41
    assion
    -0.40
    POSITIVE LOGITS
     controller
    0.91
     controllers
    0.82
     Controller
    0.82
     feedback
    0.78
    Feedback
    0.78
     Controllers
    0.76
     controlador
    0.76
     Feedback
    0.74
    CONTROLLER
    0.72
     control
    0.72
    Activations Density 0.428%

    No Known Activations