© 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. 4-GEMMASCOPE-RES-16K
    11. 3308
    Prev
    Next
    INDEX
    Explanations

    references to winners and winning events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     I
    -0.67
     most
    -0.64
     many
    -0.64
     l
    -0.56
     it
    -0.55
     Ge
    -0.54
     bit
    -0.54
    mudah
    -0.54
     Berg
    -0.54
     az
    -0.54
    POSITIVE LOGITS
     winner
    2.43
     Winner
    2.30
     winners
    2.26
     Winners
    2.08
    winner
    1.99
     WINNER
    1.97
    Winner
    1.95
    Winners
    1.85
    winners
    1.82
    WINNER
    1.62
    Activations Density 0.148%

    No Known Activations