© 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. 23-GEMMASCOPE-RES-16K
    11. 7505
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions involving variables and derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Важно
    -0.47
     hasNext
    -0.47
    #
    -0.46
    printStats
    -0.43
    SafeArea
    -0.43
     altars
    -0.43
    RegressionTest
    -0.43
     applicants
    -0.43
     exceptions
    -0.42
     ujednoznacz
    -0.42
    POSITIVE LOGITS
     transfieras
    0.53
    ')(
    0.47
     utafitiHapana
    0.43
    Legături
    0.42
     ra
    0.39
    '])->
    0.38
    ))*
    0.38
    bootstrapcdn
    0.38
    jsdelivr
    0.37
    ])*
    0.37
    Activations Density 1.926%

    No Known Activations