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. 20-GEMMASCOPE-RES-16K
    6. 4006
    Prev
    Next
    INDEX
    Explanations

    instances of error handling and duplicate entries in programming or database contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by "already" or translations of "already"

    np_acts-logits-general · gemini-2.0-flash

    already

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.79
     كومونز
    -0.65
     שוליים
    -0.62
    twimg
    -0.59
     ISNI
    -0.57
     PublicKey
    -0.57
    Einzelnachweise
    -0.55
    ViewImports
    -0.54
    initializeApp
    -0.54
    AdapterFactory
    -0.54
    POSITIVE LOGITS
     already
    4.50
    already
    4.11
     Already
    3.99
    Already
    3.85
     ALREADY
    3.51
     allerede
    2.97
    ALREADY
    2.87
     redan
    2.82
     déjà
    2.79
     이미
    2.77
    Activations Density 1.126%

    No Known Activations