Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4261
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electrical components and devices

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

    Controlled by/driving [something]

    np_acts-logits-general · gemini-2.0-flash

    driving and control operations

    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
     يتيمه
    -0.71
     للمعارف
    -0.70
    makeConstraints
    -0.65
     defaultstate
    -0.63
    AndEndTag
    -0.61
    Демографія
    -0.61
    сылкі
    -0.60
    webElementXpaths
    -0.58
    ſelf
    -0.58
    Aholisi
    -0.58
    POSITIVE LOGITS
     controller
    0.75
     Controller
    0.74
    plication
    0.61
    controller
    0.61
     management
    0.57
    Controller
    0.57
     controllers
    0.55
     control
    0.55
     управления
    0.55
     computer
    0.54
    Activations Density 0.468%

    No Known Activations