© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 5976
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate relationships and dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     varandra
    -0.63
     démocr
    -0.61
     blessés
    -0.60
     dieux
    -0.57
     vallée
    -0.57
     chré
    -0.54
     vœux
    -0.54
     militaires
    -0.53
     démission
    -0.52
     récents
    -0.52
    POSITIVE LOGITS
     AssemblyTitle
    0.82
    orianCalendar
    0.80
     >=",
    0.74
     Roskov
    0.74
     AssemblyCompany
    0.71
    GEBURTS
    0.69
    MergeFrom
    0.66
    calyp
    0.66
    XmlAccessType
    0.66
     stuff
    0.66
    Activations Density 0.578%

    No Known Activations