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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65765
    Prev
    Next
    INDEX
    Explanations

    instances of quotes or dialogues related to events or actions in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.50
     للمعارف
    -0.48
    amssymb
    -0.48
     lenker
    -0.48
    HtmlAttribute
    -0.46
     defStyleAttr
    -0.46
     NavController
    -0.46
    OGND
    -0.45
     useAppContext
    -0.45
     Италијани
    -0.45
    POSITIVE LOGITS
     somewhere
    2.81
     Somewhere
    2.38
    somewhere
    2.34
    Somewhere
    2.28
     sometime
    2.16
     someplace
    1.89
     Sometime
    1.82
     irgendwo
    1.68
     anywhere
    1.52
     algum
    1.33
    Activations Density 0.172%

    No Known Activations