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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5953
    Prev
    Next
    INDEX
    Explanations

    specific numerical data or identifiers related to products or events

    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
    rawDesc
    -0.62
     ErrIntOverflow
    -0.57
    ंदीखरीदारी
    -0.55
    hamshire
    -0.55
    Rptr
    -0.55
     PeEnEo
    -0.54
    enterOuterAlt
    -0.54
     CURIAM
    -0.54
     Majefty
    -0.54
    Autoritní
    -0.53
    POSITIVE LOGITS
     blog
    0.93
     blogging
    0.82
     Blog
    0.82
    blog
    0.82
    Blog
    0.77
     blogs
    0.77
     blogger
    0.76
     Blogging
    0.72
     bloggers
    0.70
     Blogger
    0.68
    Activations Density 0.363%

    No Known Activations