© 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. 34-GEMMASCOPE-RES-16K
    11. 7796
    Prev
    Next
    INDEX
    Explanations

    programming concepts and code related to file handling and processing in scripts

    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
    bind
    -0.28
     diha
    -0.27
     via
    -0.27
     Sap
    -0.27
     diku
    -0.26
    搅
    -0.26
     صف
    -0.26
     khóa
    -0.25
     prezen
    -0.25
     đào
    -0.23
    POSITIVE LOGITS
     extension
    1.89
     extensions
    1.68
    Extension
    1.67
    extension
    1.66
     Extension
    1.66
     EXTENSION
    1.48
     Extensions
    1.47
     extensión
    1.43
    EXTENSION
    1.40
    extensions
    1.38
    Activations Density 0.340%

    No Known Activations