© 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-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 15199
    Prev
    Next
    INDEX
    Explanations

    terms and phrases that express a negative critique or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.62
    Hentet
    -0.61
    CloseOperation
    -0.60
     vooz
    -0.60
    OGND
    -0.60
     fashiola
    -0.59
    Gön
    -0.59
     laſſen
    -0.58
    ésultats
    -0.57
    الدراسه
    -0.57
    POSITIVE LOGITS
    MigrationBuilder
    0.52
     CreateTagHelper
    0.46
     caractère
    0.42
    ness
    0.39
    WriteTagHelper
    0.38
     caráter
    0.37
     highly
    0.37
    NameInMap
    0.36
    AddHtmlAttribute
    0.35
     characteristics
    0.34
    Activations Density 0.485%

    No Known Activations