© 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. 21-GEMMASCOPE-RES-16K
    11. 11935
    Prev
    Next
    INDEX
    Explanations

    references to stakes, challenges, and high thresholds 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 @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    principalTable
    -0.64
    OGND
    -0.58
    abestanden
    -0.54
     eventdata
    -0.50
    PRWEB
    -0.48
    HandlerContext
    -0.47
     iconTwitter
    -0.44
    AlterField
    -0.44
    Портали
    -0.43
     onBind
    -0.43
    POSITIVE LOGITS
     high
    2.43
     higher
    2.17
    high
    2.16
     tinggi
    1.98
    higher
    1.88
    High
    1.87
    高
    1.84
    HIGH
    1.82
     HIGH
    1.82
     High
    1.80
    Activations Density 0.503%

    No Known Activations