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. 1527
    Prev
    Next
    INDEX
    Explanations

    references to observing or examining various subjects or scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    constructions expressing the act of examining or directing attention to something, especially the “look … at” pattern across tenses and phrasings.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    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
     يتيمه
    -0.66
     queſta
    -0.56
    stridium
    -0.55
    SharedDtor
    -0.55
    quelize
    -0.52
     kaarangay
    -0.52
    istoitu
    -0.51
    Geplaatst
    -0.51
    stylers
    -0.49
    XtraReports
    -0.47
    POSITIVE LOGITS
     examining
    0.74
     viewing
    0.70
     Examining
    0.69
     inspecting
    0.64
     Examine
    0.63
    Inspect
    0.62
     Inspect
    0.61
     view
    0.61
    examine
    0.61
     Viewing
    0.60
    Activations Density 0.308%

    No Known Activations