© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7972
    Prev
    Next
    INDEX
    Explanations

    references to the name "Jo" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    ParallelGroup
    -0.53
     AssemblyTitle
    -0.52
     AttributeSet
    -0.48
    AddHtmlAttribute
    -0.47
    addContainerGap
    -0.47
    MigrationBuilder
    -0.44
     ContentValues
    -0.44
     Autorisations
    -0.43
     kasarigan
    -0.43
     itemView
    -0.42
    POSITIVE LOGITS
    Jo
    0.89
     Jo
    0.88
     jo
    0.83
    jo
    0.75
     Joe
    0.73
     pat
    0.71
     JO
    0.69
     Джо
    0.68
     JOS
    0.68
     Jojo
    0.67
    Activations Density 1.541%

    No Known Activations