© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 8185
    Prev
    Next
    INDEX
    Explanations

    phrases indicating adherence to rules or standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    よいよ
    -0.78
    sterious
    -0.76
    전히
    -0.74
     canadien
    -0.74
     Shimizu
    -0.73
    வில்
    -0.72
    ায়
    -0.71
    チール
    -0.71
    UVWXYZ
    -0.71
    ồm
    -0.70
    POSITIVE LOGITS
    according
    0.79
     According
    0.78
     متعلقه
    0.75
    mě
    0.69
    According
    0.69
    __;
    0.68
     concor
    0.68
     according
    0.67
    libur
    0.66
     pursuant
    0.64
    Activations Density 0.151%

    No Known Activations