© 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. 20-GEMMASCOPE-RES-16K
    6. 10542
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting used in written code or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    accented Latin characters (like Ã, É, Ü, í, ó, etc.) in multilingual text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BrowserModule
    -0.69
    StoryboardSegue
    -0.66
    isContained
    -0.65
     ujednoznacz
    -0.63
     Normdatei
    -0.62
    tonode
    -0.60
    providedIn
    -0.57
    SequentialGroup
    -0.57
    awtextra
    -0.56
    CloseOperation
    -0.55
    POSITIVE LOGITS
     ethical
    0.49
     pregnant
    0.40
    <b>
    0.39
    :✨
    0.37
     wußte
    0.36
     ICT
    0.36
    logous
    0.35
     IC
    0.35
     ethics
    0.35
     Tx
    0.35
    Activations Density 0.055%

    No Known Activations