© 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. 2835
    Prev
    Next
    INDEX
    Explanations

    HTML or XML-like tags and their closure

    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
     viewDidLoad
    -0.35
     CGPoint
    -0.34
     denture
    -0.31
    šanās
    -0.31
     SwitchCompat
    -0.30
     hablado
    -0.29
     ljudi
    -0.29
    ￡
    -0.29
    ншни
    -0.28
     igång
    -0.28
    POSITIVE LOGITS
     esternos
    0.68
    
    0.67
     nahilalakip
    0.64
     مشين
    0.59
    帖最后由
    0.58
     snippetHide
    0.56
    Nikola
    0.54
    React
    0.53
    Hochspringen
    0.52
    awaiter
    0.52
    Activations Density 0.096%

    No Known Activations