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. 11990
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries related to testimonies or statements, particularly in a legal context

    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
    ciclop
    -0.55
     existir
    -0.49
     gambe
    -0.48
     idéal
    -0.47
     cím
    -0.47
    dword
    -0.47
     professionali
    -0.46
    tiembre
    -0.46
     kár
    -0.46
     rodillas
    -0.46
    POSITIVE LOGITS
     asked
    0.87
     enquired
    0.85
     IBOutlet
    0.84
    Asked
    0.82
    asked
    0.82
     Asked
    0.81
    InjectAttribute
    0.78
     queried
    0.78
     inquired
    0.76
     questioned
    0.76
    Activations Density 0.145%

    No Known Activations