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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10363
    Prev
    Next
    INDEX
    Explanations

    references to competitions and rankings in various fields

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

    preceding or related to winning competitions

    np_acts-logits-general · gemini-2.0-flash

    winner or champion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginInit
    -0.48
    λοι
    -0.46
    ThroughAttribute
    -0.44
     MotionEvent
    -0.44
    ари
    -0.44
    EndInit
    -0.44
     Glaub
    -0.43
     propOrder
    -0.42
     priests
    -0.42
    gere
    -0.42
    POSITIVE LOGITS
     winner
    1.66
     winners
    1.48
    winner
    1.35
    Winner
    1.26
     vainqueur
    1.22
    winners
    1.20
     champion
    1.19
     Winner
    1.19
     vincit
    1.17
     champions
    1.13
    Activations Density 0.171%

    No Known Activations