© 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. 38-GEMMASCOPE-RES-16K
    11. 9723
    Prev
    Next
    INDEX
    Explanations

    comparative phrases emphasizing "more than" or "better than" relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tableFuture
    -0.42
    greenrobot
    -0.42
    +#+#
    -0.40
     таки
    -0.39
    "]();
    -0.38
    又
    -0.38
    vábbi
    -0.37
     همچنین
    -0.36
    ️
    -0.36
    違った
    -0.36
    POSITIVE LOGITS
     usual
    1.04
    usual
    0.92
     expected
    0.91
     anticipated
    0.84
     prévu
    0.81
    expected
    0.80
     esperado
    0.74
     zwykle
    0.73
     ever
    0.73
     gewöhnlich
    0.73
    Activations Density 0.374%

    No Known Activations