© 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. 20-GEMMASCOPE-RES-16K
    6. 4981
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure within programming-related text

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

    programming-related tokens like "import", "class", and programming language-specific keywords and symbols.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NamedQueries
    -0.50
     ejus
    -0.43
     dAtA
    -0.43
    出版年
    -0.42
     pérd
    -0.41
     quoque
    -0.41
     tää
    -0.40
     jäsen
    -0.40
     kanssa
    -0.40
     kokona
    -0.40
    POSITIVE LOGITS
     initComponents
    1.15
     QtWidgets
    0.77
     StatelessWidget
    0.69
     OnInit
    0.66
     StatefulWidget
    0.64
    AppCompat
    0.60
     createState
    0.60
    SpringBootTest
    0.60
    __()
    0.58
    ReusableCell
    0.57
    Activations Density 0.028%

    No Known Activations