© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9477
    Prev
    Next
    INDEX
    Explanations

    references to fabric in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 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
    XmlAccessType
    -0.82
    +:+
    -0.79
     kereszt
    -0.78
    LookAnd
    -0.73
    帖最后由
    -0.69
    出版年
    -0.69
    
    -0.69
     supérieurs
    -0.68
    endphp
    -0.68
    CodeAttribute
    -0.68
    POSITIVE LOGITS
     steering
    0.88
     Steering
    0.67
     fabric
    0.64
    Steering
    0.60
     guiding
    0.58
    steering
    0.56
     Rath
    0.55
     steers
    0.55
    om
    0.55
     steered
    0.54
    Activations Density 0.174%

    No Known Activations