© 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. 14993
    Prev
    Next
    INDEX
    Explanations

    phrases and elements related to social or systemic issues, particularly those affecting interpersonal relationships and societal dynamics

    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
     مشين
    -0.77
    GraphicsUnit
    -0.59
    jspb
    -0.48
    /**
    -0.47
    CDCl
    -0.46
     betweenstory
    -0.45
    //
    -0.45
     onOptions
    -0.44
    ChildScrollView
    -0.44
    addContainerGap
    -0.44
    POSITIVE LOGITS
    KommentareTeilen
    0.64
    oa̍t
    0.55
    ྑ
    0.53
    Atsauces
    0.50
    Aholisi
    0.50
     beſte
    0.50
     Italijani
    0.49
    릭터
    0.47
    Спасылкі
    0.47
    PRWEB
    0.46
    Activations Density 1.732%

    No Known Activations