© 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. 22-GEMMASCOPE-RES-16K
    6. 9103
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to electrical switches and mechanisms

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

    Mechanical components/actions (levers, switches, actuators)

    np_acts-logits-general · gemini-2.0-flash

    mechanical actuation and control

    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
    Tembelea
    -0.64
    WebVitals
    -0.64
    kira
    -0.63
    jgl
    -0.58
    ACING
    -0.55
    最快更新
    -0.55
    IntoConstraints
    -0.54
     watermark
    -0.54
     متعلقه
    -0.53
     chale
    -0.53
    POSITIVE LOGITS
     mechanism
    1.04
     spring
    1.00
     switch
    0.99
     Mechanism
    0.93
     actuated
    0.92
    Mechanism
    0.88
     trigger
    0.87
     lever
    0.87
    mechanism
    0.87
     actu
    0.83
    Activations Density 0.629%

    No Known Activations