© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11835
    Prev
    Next
    INDEX
    Explanations

    phrases expressing possibilities or uncertainties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     handleSubmit
    -0.50
    isSuccessful
    -0.47
     Chriftian
    -0.45
     uLocal
    -0.42
     isIn
    -0.40
     éc
    -0.40
     ſp
    -0.38
     oprot
    -0.38
     outputStream
    -0.38
    subpackage
    -0.37
    POSITIVE LOGITS
     may
    1.59
    may
    1.33
     May
    1.30
     MAY
    1.27
    May
    1.22
    MAY
    1.12
     might
    1.09
     Might
    0.99
    อาจ
    0.96
     MIGHT
    0.94
    Activations Density 0.223%

    No Known Activations