© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 1237
    Prev
    Next
    INDEX
    Explanations

    terms related to messaging and communication protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     magistrate
    -0.54
     Unido
    -0.54
     propOrder
    -0.50
    ︎
    -0.49
     Schaff
    -0.49
    antart
    -0.48
     puja
    -0.48
     initWithFrame
    -0.48
     measurements
    -0.48
    Measurements
    -0.47
    POSITIVE LOGITS
    box
    0.73
    board
    0.70
    BOX
    0.67
    SBATCH
    0.62
     boîte
    0.62
     boards
    0.62
    boxes
    0.61
     boite
    0.61
    Board
    0.60
     Board
    0.59
    Activations Density 0.177%

    No Known Activations