© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 10218
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting symbols often used in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Larsson
    -0.47
     Persson
    -0.46
     Rocha
    -0.46
     Svensson
    -0.41
     Shimizu
    -0.40
     Christiansen
    -0.40
     Reiche
    -0.39
     Ribeiro
    -0.38
     Soares
    -0.36
     Lehmann
    -0.36
    POSITIVE LOGITS
    httphttps
    0.83
     snippetHide
    0.70
     pinulongan
    0.63
    ⤒
    0.61
    AnchorStyles
    0.60
     referrerpolicy
    0.57
    ReusableCell
    0.57
    EndContext
    0.57
    IMPORTED
    0.56
    outWeight
    0.56
    Activations Density 1.528%

    No Known Activations