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. 5-GEMMASCOPE-RES-16K
    6. 4893
    Prev
    Next
    INDEX
    Explanations

    references to legal statutes or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.93
     ModelExpression
    -0.78
    ValueStyle
    -0.77
    WebServlet
    -0.74
    Personendaten
    -0.72
     aikaa
    -0.70
     Persians
    -0.66
     ajutor
    -0.65
    CloseOperation
    -0.65
     itſelf
    -0.64
    POSITIVE LOGITS
     own
    1.42
     your
    1.17
     seu
    1.14
     swoje
    1.11
    Ihre
    1.06
     své
    1.06
     sua
    1.06
     their
    1.04
     svoje
    1.04
     his
    1.03
    Activations Density 0.067%

    No Known Activations