© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8650
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to grammatical structures and constructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tothe
    -0.78
     autorytatywna
    -0.68
     kasarigan
    -0.66
     zur
    -0.61
     vnto
    -0.58
    ècie
    -0.58
    #+#
    -0.57
     unto
    -0.55
    到你
    -0.55
     thereto
    -0.54
    POSITIVE LOGITS
     να
    1.05
     да
    0.91
     să
    0.73
    ที่จะ
    0.56
    ToBe
    0.54
     å
    0.53
     jā
    0.53
     te
    0.53
    要说
    0.46
    ämään
    0.43
    Activations Density 0.191%

    No Known Activations