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. 15-GEMMASCOPE-RES-16K
    6. 1654
    Prev
    Next
    INDEX
    Explanations

    information related to budget, cost efficiency, and limited resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.70
    IUrlHelper
    -0.60
    testens
    -0.55
    ApiProperty
    -0.54
    MENAFN
    -0.53
     يتيمه
    -0.53
    fris
    -0.52
     dirait
    -0.52
     ویکی‌پدیا
    -0.52
    Nationalité
    -0.51
    POSITIVE LOGITS
     limited
    1.10
    limited
    1.00
    Limited
    0.92
     Limited
    0.89
     LIMITED
    0.87
     terbatas
    0.82
     resources
    0.79
     limitado
    0.79
     meager
    0.78
    有限
    0.78
    Activations Density 0.350%

    No Known Activations