Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 13163
    Prev
    Next
    INDEX
    Explanations

    references to the concept and various forms of art

    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
     Monfieur
    -1.49
     myſelf
    -1.48
     themſelves
    -1.35
     ſever
    -1.33
     ſmall
    -1.32
     pleaſure
    -1.32
     Diſ
    -1.30
     purpoſe
    -1.23
     reaſon
    -1.22
     fevere
    -1.21
    POSITIVE LOGITS
     art
    1.61
     ART
    1.47
     Art
    1.44
     arts
    1.33
    Art
    1.31
    art
    1.29
    ART
    1.23
     Arts
    1.17
     ARTS
    1.09
     arte
    1.04
    Activations Density 0.038%

    No Known Activations