© 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. 34-GEMMASCOPE-RES-16K
    11. 10477
    Prev
    Next
    INDEX
    Explanations

    elements or structures typically associated with programming languages or data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     honneur
    -0.46
    tagHelper
    -0.42
    MessageOf
    -0.40
     Exactos
    -0.40
     rechange
    -0.40
     cardiaque
    -0.37
    WithIdentifier
    -0.36
     rescate
    -0.36
    using
    -0.35
     honor
    -0.35
    POSITIVE LOGITS
    StructEnd
    0.64
    IVEREF
    0.47
    Jeografia
    0.46
    webElementXpaths
    0.45
     __
    0.45
    iläum
    0.42
    TRIBUN
    0.42
     comuniques
    0.42
    adaptiveStyles
    0.40
    enumii
    0.39
    Activations Density 0.308%

    No Known Activations