© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 54656
    Prev
    Next
    INDEX
    Explanations

    references to reading data from files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    RTHOOK
    -0.51
    $_['
    -0.48
     wilds
    -0.47
    mobileqq
    -0.47
    GeneratedValue
    -0.46
     lots
    -0.45
    donut
    -0.44
     egos
    -0.44
    formik
    -0.44
     Illuminate
    -0.44
    POSITIVE LOGITS
    Reader
    0.88
     Reader
    0.85
     reader
    0.82
    reader
    0.76
     BufferedReader
    0.72
     READER
    0.69
     Readers
    0.63
    BufferedReader
    0.61
     readers
    0.60
    bufio
    0.60
    Activations Density 0.000%

    No Known Activations