© 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. 33-GEMMASCOPE-RES-16K
    11. 14328
    Prev
    Next
    INDEX
    Explanations

    programming language syntax, particularly related to function definitions and conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.68
    ViewFeatures
    -0.64
    mpagne
    -0.64
     betweenstory
    -0.63
    WireFormatLite
    -0.62
     HFILL
    -0.62
     invokingState
    -0.59
    NameInMap
    -0.59
    protoimpl
    -0.58
    WriteBarrier
    -0.57
    POSITIVE LOGITS
     medel
    0.40
     modificación
    0.38
     artist
    0.36
     episode
    0.36
     lesión
    0.33
     the
    0.33
     coleccion
    0.33
     device
    0.32
     cuestion
    0.31
     hoja
    0.31
    Activations Density 4.433%

    No Known Activations