© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12853
    Prev
    Next
    INDEX
    Explanations

    references to fairy tales and folklore

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mobileqq
    -0.54
     testigo
    -0.52
    tangentMode
    -0.51
    MessageTagHelper
    -0.49
    SequentialGroup
    -0.47
     localObject
    -0.47
    orghini
    -0.46
     eulogy
    -0.45
     prêtres
    -0.45
     uVar
    -0.45
    POSITIVE LOGITS
     fairy
    1.38
     Fairy
    1.22
    fairy
    1.05
    Fairy
    1.03
     fairytale
    1.01
     Märchen
    0.87
     fairies
    0.86
     Cinderella
    0.79
     FAIR
    0.73
     сказ
    0.71
    Activations Density 0.263%

    No Known Activations