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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6018
    Prev
    Next
    INDEX
    Explanations

    terms related to legal standards, specifically those concerning rights, obligations, and the consequences of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    받
    -0.55
    /-/
    -0.48
    Péri
    -0.48
    AutoField
    -0.45
    any
    -0.45
    FATAL
    -0.44
     musik
    -0.43
     spinach
    -0.43
    open
    -0.43
    I
    -0.42
    POSITIVE LOGITS
     صوتيه
    0.71
    IsContent
    0.68
     الحره
    0.64
     تضيفلها
    0.64
     AssemblyVersion
    0.62
    KommentareTeilen
    0.60
    __':
    
    0.60
     فريبيس
    0.59
    WebServlet
    0.59
    IZONA
    0.57
    Activations Density 0.554%

    No Known Activations