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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 2845
    Prev
    Next
    INDEX
    Explanations

    occurrences of exception handling phrases in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.64
    UpInside
    -0.58
    awtextra
    -0.55
     networked
    -0.54
    MigrationBuilder
    -0.53
     getEmail
    -0.52
     pinulongan
    -0.52
     intptr
    -0.50
     noDo
    -0.50
     Starbucks
    -0.50
    POSITIVE LOGITS
    CHECK
    0.78
     catch
    0.74
     CHECK
    0.60
     classify
    0.59
     classified
    0.59
     caught
    0.56
     catches
    0.56
     classification
    0.55
     Check
    0.54
     catching
    0.54
    Activations Density 0.149%

    No Known Activations