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. 16-GEMMASCOPE-RES-16K
    6. 4961
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to data structures and methods

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

    Code related to printing or displaying data

    np_acts-logits-general · gemini-2.0-flash

    printing and displaying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Commencez
    -0.51
     schaffen
    -0.43
     botão
    -0.43
    öpfer
    -0.43
    vlád
    -0.42
     löytyy
    -0.42
     parseFrom
    -0.42
     деле
    -0.41
    妥
    -0.41
    ActionCreators
    -0.41
    POSITIVE LOGITS
     pprint
    0.80
     listing
    0.75
     display
    0.75
     print
    0.75
     displaying
    0.73
     showing
    0.73
     showcase
    0.73
     showcasing
    0.73
     printout
    0.72
    enumi
    0.72
    Activations Density 0.179%

    No Known Activations