© 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. 11-GEMMASCOPE-RES-16K
    11. 10485
    Prev
    Next
    INDEX
    Explanations

    various types of underscores and related formatting characters in the content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.69
     للاسماء
    -0.68
    LookAnd
    -0.64
    RegressionTest
    -0.64
    windowFixed
    -0.64
     propOrder
    -0.63
    RotationOrder
    -0.62
     AssemblyTitle
    -0.62
    tonode
    -0.61
    uxxxx
    -0.60
    POSITIVE LOGITS
    AxisAlignment
    0.47
     the
    0.46
     new
    0.38
     pure
    0.37
    OwnProperty
    0.36
     native
    0.35
     potential
    0.35
     nouvel
    0.35
     wet
    0.35
     biology
    0.34
    Activations Density 0.415%

    No Known Activations