© 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. 22-GEMMASCOPE-RES-16K
    6. 6183
    Prev
    Next
    INDEX
    Explanations

    terminology related to gaming mechanics and coding functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ジャック
    -0.36
     model
    -0.34
     Plaintiff
    -0.33
    UnitTesting
    -0.33
    魔鬼
    -0.32
     Model
    -0.31
     Latin
    -0.31
     expressed
    -0.31
     WINNER
    -0.31
    Uint
    -0.30
    POSITIVE LOGITS
    
    0.72
     الرياضيه
    0.66
    WriteTagHelper
    0.64
     HttpNotFound
    0.63
     estekak
    0.60
    httphttps
    0.58
    InitStruct
    0.57
     snippetHide
    0.55
    ImageContext
    0.54
     vPvB
    0.52
    Activations Density 0.409%

    No Known Activations