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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5965
    Prev
    Next
    INDEX
    Explanations

    mention of characters and their actions or attributes in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessFile
    -0.56
     ویکی‌پدی
    -0.52
     nahilalakip
    -0.52
     estekak
    -0.47
    
    -0.46
     مرئيه
    -0.46
    ngrx
    -0.43
     Javan
    -0.42
     Taliban
    -0.42
    Wiley
    -0.42
    POSITIVE LOGITS
     Rin
    0.53
     classmates
    0.50
     ts
    0.49
     classmate
    0.49
     Yuk
    0.49
     Kou
    0.48
    Rin
    0.48
     yuri
    0.48
     kou
    0.48
     Tou
    0.47
    Activations Density 0.596%

    No Known Activations