© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14405
    Prev
    Next
    INDEX
    Explanations

    references to patents and legal terminology related to biological and ecological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zweiten
    -0.40
     biß
    -0.39
     Säure
    -0.38
     rač
    -0.38
     Bewußt
    -0.37
     mêmes
    -0.37
     Gegenteil
    -0.36
     aynı
    -0.36
     Durchmesser
    -0.35
     behoort
    -0.35
    POSITIVE LOGITS
    URLException
    0.62
     AssemblyCulture
    0.56
     المعرف
    0.53
    ⤹
    0.52
     dafs
    0.51
     queſta
    0.51
     dispen
    0.51
    PMS
    0.51
     fubject
    0.50
     ſmall
    0.50
    Activations Density 0.405%

    No Known Activations