© 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. 36-GEMMASCOPE-RES-16K
    11. 8014
    Prev
    Next
    INDEX
    Explanations

    references to celebrities and their personal lives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.69
     ModelExpression
    -0.60
    fjspx
    -0.59
    KommentareTeilen
    -0.58
     noDo
    -0.55
    发表于
    -0.51
    IntoConstraints
    -0.51
    
    -0.50
    UrlResolution
    -0.50
    OGND
    -0.50
    POSITIVE LOGITS
     former
    1.02
     veteran
    0.87
    former
    0.79
    Former
    0.73
     Former
    0.69
     prolific
    0.69
    这位
    0.65
     diminutive
    0.63
     talented
    0.63
     outspoken
    0.62
    Activations Density 0.297%

    No Known Activations