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

    Neuronpedia

    Jacobian LensNEW
    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. 2-GEMMASCOPE-RES-16K
    11. 5674
    Prev
    Next
    INDEX
    Explanations

    references to positions of prominence or ranking, particularly the word "top."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    뀐
    -0.50
     commits
    -0.48
    뀌
    -0.47
    前世
    -0.47
    BeginInit
    -0.45
     fermo
    -0.44
    commitment
    -0.43
    quartered
    -0.42
    voltaic
    -0.42
    prepareStatement
    -0.41
    POSITIVE LOGITS
     pères
    0.56
     fathers
    0.53
     Fathers
    0.51
    usercontent
    0.47
     Father
    0.45
    寻常
    0.45
    TagNumber
    0.44
     bread
    0.42
    Father
    0.41
    Bread
    0.41
    Activations Density 0.091%

    No Known Activations