© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 14197
    Prev
    Next
    INDEX
    Explanations

    statements expressing knowledge, assurance, or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yourself
    -1.14
     yourselves
    -0.93
     your
    -0.89
     Yourself
    -0.78
    yourself
    -0.75
     می‌توانید
    -0.73
     YOURSELF
    -0.66
    your
    -0.65
     ваших
    -0.62
     jezelf
    -0.62
    POSITIVE LOGITS
     you
    0.75
     thee
    0.71
     Thee
    0.64
     vocês
    0.63
     بتوان
    0.63
     препратки
    0.61
     YOU
    0.61
    tvguidetime
    0.60
    Thee
    0.59
     محفوظة
    0.59
    Activations Density 0.272%

    No Known Activations