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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 14310
    Prev
    Next
    INDEX
    Explanations

    phrases related to ethical approval and institutional review in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.81
    ंदीखरीदारी
    -0.70
     FetchType
    -0.60
    RenderAtEndOf
    -0.60
     snippetHide
    -0.60
    లాలు
    -0.59
    <?
    -0.59
    Kaynakça
    -0.57
    AlterField
    -0.56
    ValueStyle
    -0.55
    POSITIVE LOGITS
     authorities
    1.53
     Commission
    1.52
     commission
    1.50
     Authority
    1.46
     committee
    1.44
     authority
    1.43
     board
    1.36
     Board
    1.36
     Committee
    1.35
     Authorities
    1.29
    Activations Density 0.747%

    No Known Activations