© 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. 31-GEMMASCOPE-RES-16K
    11. 6927
    Prev
    Next
    INDEX
    Explanations

    references to a specific brand associated with promotional offers and discounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    brand names and proper nouns, particularly "Mario Badescu" repeated throughout spam-like promotional content.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.51
    iseite
    -0.47
    WriteBarrier
    -0.46
     Bochum
    -0.45
    цезда
    -0.45
     dramatique
    -0.45
    intervento
    -0.44
    SourceChecksum
    -0.43
     sagrado
    -0.43
     inoxidable
    -0.43
    POSITIVE LOGITS
     Mario
    0.90
    Mario
    0.81
     mario
    0.71
     Bowser
    0.68
    mario
    0.65
     Toad
    0.62
     Koo
    0.57
     luigi
    0.57
     Mushroom
    0.56
     Luigi
    0.56
    Activations Density 0.059%

    No Known Activations