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. 8-GEMMASCOPE-RES-16K
    6. 11258
    Prev
    Next
    INDEX
    Explanations

    references to durability and lifespan of products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.63
    tinyos
    -0.60
    مصادر
    -0.58
    зулта
    -0.57
    GEBURTSDATUM
    -0.54
     nakalista
    -0.54
    IActionResult
    -0.53
    tvguidetime
    -0.53
     Murcia
    -0.52
    QMetaType
    -0.52
    POSITIVE LOGITS
     noqa
    0.60
     retires
    0.59
     age
    0.58
     usia
    0.58
     wear
    0.56
    ündigt
    0.55
     expire
    0.54
     ciclos
    0.54
     retire
    0.54
    drawSprites
    0.53
    Activations Density 0.264%

    No Known Activations