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. 5812
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations

    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
    rungsseite
    -0.65
    IUrlHelper
    -0.61
     lenker
    -0.59
     Biôgrafia
    -0.59
    GeneratedCode
    -0.57
    RegistryLite
    -0.57
     ویکی‌پدی
    -0.56
    #+#
    -0.56
    agram
    -0.56
    SuppressMessage
    -0.55
    POSITIVE LOGITS
     AssemblyCulture
    0.62
    GraphicsUnit
    0.47
     betweenstory
    0.46
    @[+][
    0.45
    classnames
    0.45
    amerikanischer
    0.42
    Leaks
    0.42
    hdashline
    0.41
     }^{(
    0.40
    مارات
    0.40
    Activations Density 0.798%

    No Known Activations