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. 21-GEMMASCOPE-RES-16K
    6. 13795
    Prev
    Next
    INDEX
    Explanations

    text relating to theatrical productions, particularly those associated with historical figures and events in theater

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.55
     myſelf
    -1.54
     Jefus
    -1.43
    ſelf
    -1.42
    ſelves
    -1.39
     ſever
    -1.38
     pleaſure
    -1.37
     faſt
    -1.35
     Majefty
    -1.34
     themſelves
    -1.32
    POSITIVE LOGITS
     geven
    0.58
    jsdelivr
    0.51
    makeConstraints
    0.47
    context
    0.46
    listdir
    0.46
    <bos>
    0.45
     ma
    0.44
     entende
    0.43
     desain
    0.41
     entendido
    0.41
    Activations Density 0.075%

    No Known Activations