© 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. 24-GEMMASCOPE-RES-16K
    6. 2017
    Prev
    Next
    INDEX
    Explanations

    code and function declarations that involve compatibility checks or configurations

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

    Code snippets and uncommon words

    np_acts-logits-general · gemini-2.0-flash

    relief and rubber

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.67
     autorytatywna
    -0.63
    Билгалдахарш
    -0.61
    PMailer
    -0.59
    
    -0.58
    DockStyle
    -0.57
    ьаж
    -0.56
     <<<<<<<<<<<<<<
    -0.54
     OMITBAD
    -0.54
     ویکی‌پدیای
    -0.53
    POSITIVE LOGITS
     ModelExpression
    0.39
     dolayı
    0.36
    attutto
    0.36
     roulant
    0.35
    Comprom
    0.34
     compromis
    0.34
    criptors
    0.34
    ichtig
    0.34
    Enumerated
    0.34
     brewing
    0.33
    Activations Density 0.467%

    No Known Activations