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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11634
    Prev
    Next
    INDEX
    Explanations

    references to authors and authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    ########.
    -0.68
    parsedMessage
    -0.60
    delwed
    -0.59
    odeon
    -0.57
     سكانية
    -0.56
    sizeCache
    -0.55
    basicConfig
    -0.55
    didSet
    -0.55
    ("/:
    -0.55
     Geraldine
    -0.55
    POSITIVE LOGITS
     Author
    1.13
     author
    1.10
    Author
    1.07
     authors
    1.05
    author
    1.05
     Authors
    0.99
    Authors
    0.93
     AUTHOR
    0.93
    AUTHOR
    0.92
    authors
    0.91
    Activations Density 0.116%

    No Known Activations