© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 3464
    Prev
    Next
    INDEX
    Explanations

    terms related to mechanical maintenance and repair processes

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

    before services related to mechanics/technicians

    np_acts-logits-general · gemini-2.0-flash

    automotive repair technicians

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HttpNotFound
    -0.63
    witzerland
    -0.57
    setViewportView
    -0.56
     sweeteners
    -0.56
    adə
    -0.55
     Babi
    -0.53
    Rhestr
    -0.53
    зайн
    -0.53
    variates
    -0.53
    coration
    -0.53
    POSITIVE LOGITS
     repair
    1.16
     Repair
    1.05
    repair
    0.99
     repairs
    0.95
    Repair
    0.95
     repairing
    0.90
     Reparatur
    0.85
     REPAIR
    0.85
     réparation
    0.84
     diagnostic
    0.83
    Activations Density 0.192%

    No Known Activations