© 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. 9-GEMMASCOPE-RES-16K
    11. 1635
    Prev
    Next
    INDEX
    Explanations

    references to prior studies and their results within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.91
    ंदीखरीदारी
    -0.83
    FormTagHelper
    -0.82
    Jereo
    -0.81
    CloseOperation
    -0.80
     فريبيس
    -0.77
    IntoConstraints
    -0.76
    
    -0.75
    principalColumn
    -0.73
    GEBURTSDATUM
    -0.70
    POSITIVE LOGITS
     reported
    0.71
     previously
    0.69
     previous
    0.54
     published
    0.53
    previously
    0.52
     suggested
    0.51
     authors
    0.50
    reported
    0.50
     proposed
    0.50
     cited
    0.49
    Activations Density 2.399%

    No Known Activations