© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103528
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical data or metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     Middle
    -0.38
     indeed
    -0.35
    Middle
    -0.34
     specifically
    -0.33
     Far
    -0.32
     ‘
    -0.32
    Fail
    -0.32
    Vaata
    -0.31
    REC
    -0.31
     now
    -0.31
    POSITIVE LOGITS
    +#+#
    0.68
     modelAndView
    0.58
     kasarigan
    0.57
    AndEndTag
    0.56
    oredCriteria
    0.54
    RTLR
    0.53
    opress
    0.52
    scribers
    0.51
    MigrationBuilder
    0.51
    styleType
    0.50
    Activations Density 0.199%

    No Known Activations