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. 13000
    Prev
    Next
    INDEX
    Explanations

    references to specific standards, codes, or formats, particularly in a technical or scientific 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
    ias
    -0.42
    িয়
    -0.39
     magasiner
    -0.38
    ```
    -0.37
    rawa
    -0.37
    prüche
    -0.37
    tidae
    -0.37
     다
    -0.36
    NSMutable
    -0.36
    name
    -0.36
    POSITIVE LOGITS
    webElement
    0.94
    DrawerToggle
    0.86
    UnsafeEnabled
    0.84
    AddHtmlAttribute
    0.82
     nakalista
    0.79
    IntoConstraints
    0.79
    basicConfig
    0.78
     ImportError
    0.77
    AndEndTag
    0.77
    astéroïdes
    0.77
    Activations Density 1.184%

    No Known Activations