© 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. 0-GEMMASCOPE-RES-16K
    6. 10283
    Prev
    Next
    INDEX
    Explanations

    references to Amazon Web Services and its components

    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
    enumii
    -0.65
    httphttps
    -0.62
    DockStyle
    -0.60
     betweenstory
    -0.55
    ViewFeatures
    -0.54
    webElementXpaths
    -0.54
     Chwiliwch
    -0.54
    MessageOf
    -0.53
    standers
    -0.52
    TagMode
    -0.51
    POSITIVE LOGITS
    nieren
    0.45
     nest
    0.40
     boring
    0.37
     alright
    0.36
     Boring
    0.36
     boil
    0.36
    Boring
    0.35
     aggregation
    0.35
     بو
    0.35
     купа
    0.35
    Activations Density 1.945%

    No Known Activations