© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 15209
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gegner
    -0.60
     Deutscher
    -0.59
     Maske
    -0.59
     Autorin
    -0.57
     święta
    -0.57
     Erben
    -0.56
     akcji
    -0.56
     TÉCNICA
    -0.55
     Kriege
    -0.54
     Präsidenten
    -0.53
    POSITIVE LOGITS
    NOPQRST
    0.68
    спи
    0.57
    phrag
    0.56
     Synchron
    0.55
    IMPORTED
    0.55
    tablename
    0.55
    sucurs
    0.55
    izophren
    0.54
    кобрита
    0.54
    ichio
    0.53
    Activations Density 3.079%

    No Known Activations