© 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. 21-GEMMASCOPE-RES-16K
    6. 13593
    Prev
    Next
    INDEX
    Explanations

    references to crowdfunding and support for individuals or causes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ніципалі
    -0.50
     demografica
    -0.50
    DMETHOD
    -0.45
    CPtr
    -0.44
     shadowed
    -0.44
    泡
    -0.42
     betweenstory
    -0.42
    밌
    -0.41
    verifyException
    -0.41
    PreferredItem
    -0.41
    POSITIVE LOGITS
     fundraising
    0.96
     fundraiser
    0.85
     donations
    0.84
     fund
    0.82
     funds
    0.79
     Donations
    0.79
     GoFundMe
    0.78
     Funds
    0.72
     donation
    0.72
     Fundraising
    0.71
    Activations Density 0.148%

    No Known Activations