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. 3-GEMMASCOPE-RES-16K
    6. 9659
    Prev
    Next
    INDEX
    Explanations

    terms related to hearing devices and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    didSet
    -0.67
    oredCriteria
    -0.62
     '\\;'
    -0.55
     ujednoznacz
    -0.54
     imageNamed
    -0.53
    __).
    -0.52
    Izvori
    -0.52
    Kjelder
    -0.50
    ModelAttribute
    -0.50
    gouv
    -0.50
    POSITIVE LOGITS
     projector
    0.83
     compressor
    0.78
     apparatus
    0.78
     equipment
    0.76
     machines
    0.76
     calculator
    0.73
     aparat
    0.72
     projectors
    0.71
     Gerät
    0.70
     microscope
    0.70
    Activations Density 1.057%

    No Known Activations