© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3-GEMMASCOPE-RES-16K
    11. 6743
    Prev
    Next
    INDEX
    Explanations

    comments and annotations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CrossRef
    -0.58
     ujednoznacz
    -0.55
    Sklici
    -0.54
     samym
    -0.48
    twimg
    -0.46
     اینکه
    -0.46
    期刊论文
    -0.45
     épic
    -0.45
    地说道
    -0.44
    ObjectModel
    -0.44
    POSITIVE LOGITS
    UnusedPrivate
    0.50
    Either
    0.47
    Enllaces
    0.47
     @"/
    0.41
     Either
    0.41
    adaptiveStyles
    0.41
     either
    0.40
    Lähteet
    0.40
    しゅ
    0.40
    tableFuture
    0.38
    Activations Density 0.056%

    No Known Activations