© 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. 6718
    Prev
    Next
    INDEX
    Explanations

    programming functions and data structures related to creating directed graphs and initializing various components

    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
    Catégorie
    -0.34
     satisfecho
    -0.34
    HasIndex
    -0.34
    endpush
    -0.33
     CURLOPT
    -0.33
     onPostExecute
    -0.33
    GroupBox
    -0.32
     camps
    -0.32
    oneofs
    -0.32
     trov
    -0.31
    POSITIVE LOGITS
     blank
    0.64
    Autoritní
    0.63
    Blank
    0.56
    createNewFile
    0.55
    setDefault
    0.54
     initialise
    0.52
     default
    0.51
     kosong
    0.51
     defaulted
    0.51
     Blank
    0.50
    Activations Density 0.374%

    No Known Activations