Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13122
    Prev
    Next
    INDEX
    Explanations

    materials and finishes related to products

    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
    ArgsConstructor
    -0.79
    IonicModule
    -0.70
     kasarigan
    -0.64
    TagMode
    -0.64
    يميديا
    -0.58
    Portail
    -0.57
    addContainerGap
    -0.57
     Slaughter
    -0.56
    moveToFirst
    -0.56
     stationery
    -0.55
    POSITIVE LOGITS
    coat
    0.83
     coating
    0.83
     coatings
    0.79
     gloss
    0.69
     surface
    0.68
     paint
    0.68
     varnish
    0.68
     Coating
    0.67
     coats
    0.66
     coat
    0.66
    Activations Density 0.219%

    No Known Activations