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. 11409
    Prev
    Next
    INDEX
    Explanations

    snippets of programming syntax or code structures

    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
    IBarButtonItem
    -0.40
     Masyarakat
    -0.28
    saraba
    -0.27
    resizingMask
    -0.27
     Wilayah
    -0.26
    Martin
    -0.25
    Robert
    -0.24
    PyExc
    -0.24
     Arbeit
    -0.24
    BIOGRAPHY
    -0.24
    POSITIVE LOGITS
     nakalista
    0.78
    出版年
    0.74
     resourceCulture
    0.70
    :✨
    0.67
     bezeichneter
    0.62
    ロウィン
    0.60
     Normdatei
    0.59
     mergeFrom
    0.59
    expandindo
    0.59
    CodedInputStream
    0.58
    Activations Density 0.288%

    No Known Activations