© 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. 0-GEMMASCOPE-RES-16K
    11. 13042
    Prev
    Next
    INDEX
    Explanations

    references to "triple" in various contexts, often indicating a significant concept or item

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vician
    -0.68
     Polres
    -0.55
    SPATH
    -0.48
     Polsek
    -0.47
     Réponses
    -0.47
    Dichloroethane
    -0.45
    lorette
    -0.44
    
    -0.44
     dormitórios
    -0.44
     VizieR
    -0.43
    POSITIVE LOGITS
     triple
    1.35
     trio
    1.15
    triple
    1.08
     three
    1.04
     Triple
    1.00
     trilogy
    0.95
    Triple
    0.94
    三
    0.93
     triples
    0.91
    three
    0.89
    Activations Density 1.181%

    No Known Activations