© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 8792
    Prev
    Next
    INDEX
    Explanations

    alphanumeric sequences and correspondences in citations or references in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.88
    expandindo
    -0.82
    хьтан
    -0.81
     otomatig
    -0.79
    uxxxx
    -0.77
     snippetHide
    -0.77
     autorytatywna
    -0.73
    MENAFN
    -0.73
     يتيمه
    -0.73
    
    -0.73
    POSITIVE LOGITS
    $\
    0.33
     Commission
    0.31
     $\
    0.31
     Greek
    0.30
     James
    0.29
     
    0.29
     George
    0.29
    TypedValue
    0.28
     Ag
    0.27
     Mark
    0.27
    Activations Density 0.224%

    No Known Activations