© 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. 31-GEMMASCOPE-RES-16K
    6. 11685
    Prev
    Next
    INDEX
    Explanations

    references to technical concepts or methodologies in various contexts

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

    numerical data and citations in technical or academic writing.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTS
    -0.36
    énieur
    -0.34
    expandindo
    -0.33
     betweenstory
    -0.33
    GeoNames
    -0.32
    唆
    -0.32
     Prediction
    -0.32
    aarrggbb
    -0.32
    zieć
    -0.31
    AppendLine
    -0.31
    POSITIVE LOGITS
     demonstrating
    2.48
     demonstrate
    2.48
     showing
    2.41
     show
    2.28
     demonstrates
    2.27
     demonstration
    2.19
     demonstrated
    2.14
     Showing
    2.14
    showing
    2.13
    demon
    2.11
    Activations Density 1.036%

    No Known Activations