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. 12-GEMMASCOPE-RES-16K
    6. 2676
    Prev
    Next
    INDEX
    Explanations

    actions and events related to sports plays, particularly those involving passing, defensive moves, and scoring opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    нат
    -0.50
    cton
    -0.45
    шни
    -0.45
    osaurus
    -0.44
     pittura
    -0.43
    ш
    -0.42
     skimage
    -0.41
    ublic
    -0.41
    zają
    -0.41
     scala
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.87
    writeField
    0.86
    CodedInputStream
    0.85
     Wikimedijinoj
    0.83
    ंदीखरीदारी
    0.74
    InputTagHelper
    0.70
    abetes
    0.70
    bootstrapcdn
    0.70
     Normdatei
    0.68
    LabelTagHelper
    0.68
    Activations Density 0.176%

    No Known Activations