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. 17-GEMMASCOPE-RES-16K
    6. 5922
    Prev
    Next
    INDEX
    Explanations

    patterns related to data structures or variables

    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
    ########.
    -0.52
    TintMode
    -0.50
    GEBURTSDATUM
    -0.49
     ivelany
    -0.49
    ocardial
    -0.47
    rxjs
    -0.46
    Oneof
    -0.46
    AccessorTable
    -0.45
    freopen
    -0.45
     dapp
    -0.45
    POSITIVE LOGITS
     Unicode
    0.88
     unicode
    0.75
    Unicode
    0.74
    aronder
    0.66
     تضيفلها
    0.66
     undocumented
    0.62
    ranges
    0.60
     encoding
    0.59
     hexadecimal
    0.59
     untranslated
    0.59
    Activations Density 1.181%

    No Known Activations