© 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-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 15372
    Prev
    Next
    INDEX
    Explanations

    references to unique and unconventional characteristics in creative expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    日閲覧
    -0.59
     समीक्षक
    -0.58
    CodeAttribute
    -0.57
    ьаж
    -0.57
     AppDelegate
    -0.56
    QUADS
    -0.56
    AutoScaleMode
    -0.55
    EndContext
    -0.54
    AddTagHelper
    -0.54
     Italijani
    -0.54
    POSITIVE LOGITS
     eccentric
    1.04
     unconventional
    0.94
     quirky
    0.93
     wacky
    0.85
     maverick
    0.83
     uniqueness
    0.81
     unor
    0.81
     unique
    0.79
     eccentricity
    0.74
     flamboyant
    0.74
    Activations Density 0.302%

    No Known Activations