© 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. 1-GEMMASCOPE-RES-16K
    11. 412
    Prev
    Next
    INDEX
    Explanations

    phrases indicating attribution or reporting of speech and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bénévol
    -0.35
     maș
    -0.33
     bruge
    -0.32
     voľ
    -0.30
    术
    -0.30
     pauvres
    -0.29
     définiti
    -0.29
    杀了
    -0.28
     menak
    -0.28
     ordres
    -0.28
    POSITIVE LOGITS
     said
    0.94
    وأضاف
    0.91
    said
    0.79
     remarked
    0.79
     SAID
    0.73
     noted
    0.71
     testified
    0.70
    Said
    0.69
     stated
    0.69
     explicó
    0.69
    Activations Density 0.403%

    No Known Activations