© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 46895
    Prev
    Next
    INDEX
    Explanations

    instances of the term "reader" and its variations in relation to programming

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

    reader

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    addGap
    -0.52
     Cull
    -0.52
     five
    -0.52
     Knox
    -0.51
    cotch
    -0.50
     Neuf
    -0.50
     Big
    -0.49
     Islamic
    -0.49
     Kill
    -0.48
     Mull
    -0.48
    POSITIVE LOGITS
     Reader
    1.23
     reader
    1.19
    Reader
    1.18
    reader
    1.17
     READER
    1.08
     Readers
    0.91
    eader
    0.91
    readers
    0.90
     readers
    0.87
    NewReader
    0.86
    Activations Density 0.005%

    No Known Activations