© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 2888
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of responsibility or failure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Raiders
    -0.69
     Bár
    -0.66
     Roanoke
    -0.64
    "><?=
    -0.63
     recevez
    -0.63
     jugé
    -0.62
     WERE
    -0.62
     ricar
    -0.62
     Eunice
    -0.62
     mists
    -0.61
    POSITIVE LOGITS
     been
    1.05
     have
    0.93
     has
    0.92
     had
    0.85
    ve
    0.78
     оригіналу
    0.77
    >({
    0.72
     Ive
    0.71
    httphttps
    0.71
     Has
    0.68
    Activations Density 0.108%

    No Known Activations