© 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. 10547
    Prev
    Next
    INDEX
    Explanations

    statistical data and percentages related to studies or analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    listdir
    -0.46
     känna
    -0.45
     eenig
    -0.45
     enamorado
    -0.44
     eenige
    -0.43
     auroit
    -0.43
     tää
    -0.43
     känns
    -0.42
     älskar
    -0.42
     cielos
    -0.42
    POSITIVE LOGITS
     الرياضيه
    0.50
    MessageTagHelper
    0.47
     sweetener
    0.46
    ButtonStyle
    0.46
    opsida
    0.46
     pse
    0.45
     toddler
    0.45
     Bug
    0.45
     Sequoia
    0.45
     Budi
    0.45
    Activations Density 0.642%

    No Known Activations