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. 14-GEMMASCOPE-RES-16K
    6. 3032
    Prev
    Next
    INDEX
    Explanations

    specific nouns related to architecture, design, and structural components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posedge
    -0.57
     utafitiHapana
    -0.52
    thâu
    -0.52
     pinta
    -0.50
    writeFile
    -0.49
    imedia
    -0.49
    dition
    -0.48
    diel
    -0.48
     Zahlung
    -0.47
    BURGH
    -0.47
    POSITIVE LOGITS
    titleMargin
    0.80
    setupUi
    0.79
    ContentAlignment
    0.75
    RenderAtEndOf
    0.74
    StructEnd
    0.73
    TintMode
    0.70
    ConstraintMaker
    0.68
     varandra
    0.67
    kepada
    0.66
     catalana
    0.65
    Activations Density 0.462%

    No Known Activations