© 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 EvalsExportsinterp-engineNEWAPI 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. 15378
    Prev
    Next
    INDEX
    Explanations

    patterns of repetition or matching data

    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
     retraite
    -0.39
    cheduler
    -0.39
     slou
    -0.38
    Шаг
    -0.37
     roleId
    -0.37
     climb
    -0.37
    ⅘
    -0.35
    roleId
    -0.35
    jsonPath
    -0.35
     miesz
    -0.35
    POSITIVE LOGITS
     matches
    0.88
    matches
    0.86
     fits
    0.82
    Matches
    0.77
     Matches
    0.73
     colleague
    0.66
    fits
    0.61
     Fits
    0.60
     coincides
    0.59
    Fits
    0.58
    Activations Density 0.082%

    No Known Activations