© 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. 12-GEMMASCOPE-RES-16K
    11. 2488
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer architecture and medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.68
    hoeddwyd
    -0.64
     deſt
    -0.59
     zoude
    -0.57
     Numerade
    -0.57
    AnimationsModule
    -0.54
    oneofs
    -0.54
     fashiola
    -0.53
    webElementXpaths
    -0.52
     transfieras
    -0.52
    POSITIVE LOGITS
    InitStruct
    0.46
    つ
    0.36
     typical
    0.33
    vyš
    0.33
     narrow
    0.30
     thin
    0.30
    jScrollPane
    0.29
     ponta
    0.29
    thin
    0.28
    prüfung
    0.28
    Activations Density 2.531%

    No Known Activations