© 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. 14-GEMMASCOPE-RES-16K
    11. 6750
    Prev
    Next
    INDEX
    Explanations

    code-related elements and attributes in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pyx
    -0.40
    rália
    -0.33
    nables
    -0.33
    DUT
    -0.32
     proveedor
    -0.32
    AsNil
    -0.31
    (__('
    -0.31
    enderror
    -0.30
     américains
    -0.30
    帐
    -0.30
    POSITIVE LOGITS
    
    6.75
    
    1.03
    adaptiveStyles
    0.94
     defaultstate
    0.84
    ViewFeatures
    0.80
    rungsseite
    0.79
     שוליים
    0.78
    脚注の使い方
    0.77
     nahilalakip
    0.72
     CreateTagHelper
    0.71
    Activations Density 0.001%

    No Known Activations