© 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. 8601
    Prev
    Next
    INDEX
    Explanations

    references to time and specific events

    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
     bomba
    -0.34
    addGap
    -0.33
    PagerAdapter
    -0.32
    MemberId
    -0.32
    oton
    -0.32
    人人
    -0.32
     zak
    -0.31
    啄
    -0.31
     Gew
    -0.31
    Bill
    -0.31
    POSITIVE LOGITS
    +#+#
    0.74
     poveznice
    0.71
    UnusedPrivate
    0.65
    ----</
    0.63
    Rptr
    0.63
    SequentialGroup
    0.61
    ">//
    0.60
    errHandler
    0.60
    GOTREF
    0.60
    
    0.58
    Activations Density 0.766%

    No Known Activations