© 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. 13412
    Prev
    Next
    INDEX
    Explanations

    phrases related to attempts and negotiations within a political or contractual context

    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
    显
    -0.30
    Zer
    -0.29
     Eleven
    -0.29
     außergewöhn
    -0.29
    Eleven
    -0.28
    CodeAttribute
    -0.28
    渐
    -0.28
    besch
    -0.28
     doubling
    -0.27
     brand
    -0.27
    POSITIVE LOGITS
     unsuccessfully
    0.74
     aborted
    0.61
     failed
    0.60
    -------------</
    0.60
     attempted
    0.59
     ब्रेकडाउन
    0.59
    новниш
    0.59
    AsUp
    0.58
    XmlRootElement
    0.57
     proposed
    0.56
    Activations Density 0.487%

    No Known Activations