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. 11-GEMMASCOPE-RES-16K
    6. 6909
    Prev
    Next
    INDEX
    Explanations

    terms related to viral components and their properties

    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
    UnsafeEnabled
    -0.78
    !*\
    -0.74
    sizeCache
    -0.67
     дописавши
    -0.65
    providedIn
    -0.64
    PageRoute
    -0.64
    IsContent
    -0.64
     ويكيميديا
    -0.63
     defaultstate
    -0.63
     onOptions
    -0.63
    POSITIVE LOGITS
     Loth
    0.49
     بلکه
    0.49
     Standby
    0.47
    endiri
    0.47
     Stonehenge
    0.46
     ourselves
    0.46
    eBay
    0.44
     playgrounds
    0.44
     sondern
    0.44
     Tef
    0.43
    Activations Density 0.404%

    No Known Activations