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. 17-GEMMASCOPE-RES-16K
    6. 11015
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -0.55
    PHONY
    -0.51
    Preco
    -0.50
     Introduced
    -0.50
    Introduced
    -0.49
    bookings
    -0.49
    cxx
    -0.48
    shadowOpacity
    -0.48
     degradability
    -0.48
    DrawerLayout
    -0.47
    POSITIVE LOGITS
    ScopeManager
    0.69
     disponibilités
    0.66
    "}")
    0.64
    []>(
    0.60
     >=",
    0.59
     faſt
    0.59
     diza
    0.58
    fml
    0.57
    @[+][
    0.56
     Beep
    0.56
    Activations Density 0.038%

    No Known Activations