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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 187
    Prev
    Next
    INDEX
    Explanations

    references to various types of devices

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

    technical or technological terms related to devices.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ắng
    -0.44
     Мексичка
    -0.44
    retudo
    -0.42
     administratif
    -0.42
     inflationary
    -0.42
     desem
    -0.41
     Administração
    -0.41
    InSection
    -0.40
     seluruh
    -0.40
    isNullOrEmpty
    -0.40
    POSITIVE LOGITS
     Device
    1.23
     device
    1.22
    device
    1.18
    Device
    1.16
     DEVICE
    1.14
     Devices
    1.09
     devices
    1.07
     DEVICES
    1.01
    DEVICE
    1.01
    Devices
    1.00
    Activations Density 0.091%

    No Known Activations