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. 6288
    Prev
    Next
    INDEX
    Explanations

    attributes related to architectural features and structural elements

    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
    -0.59
     ProtoMessage
    -0.56
     خارجية
    -0.55
     CreateTagHelper
    -0.51
    uldig
    -0.49
    ofür
    -0.49
    PINES
    -0.48
    viewDidLoad
    -0.48
    Spoljašnje
    -0.47
    ValueStyle
    -0.47
    POSITIVE LOGITS
     opening
    0.94
     door
    0.93
     openings
    0.90
     windows
    0.90
     doors
    0.88
     window
    0.86
     ventanas
    0.79
     åp
    0.77
     öpp
    0.77
    door
    0.76
    Activations Density 0.389%

    No Known Activations