© 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. 1-GEMMASCOPE-RES-16K
    11. 6821
    Prev
    Next
    INDEX
    Explanations

    repeated informational log entries or vectors 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 @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Youth
    -0.54
     ini
    -0.50
    InvalidProtocol
    -0.49
     l
    -0.47
     him
    -0.46
     Etats
    -0.46
    ListActivity
    -0.46
    ള്ള
    -0.46
    Youth
    -0.45
     bit
    -0.45
    POSITIVE LOGITS
     itſelf
    1.34
     myſelf
    1.18
     Majefty
    1.08
     Houſe
    1.08
     Monfieur
    1.05
     houſe
    1.01
     Reſ
    1.00
     himſelf
    1.00
     ―――――
    1.00
     Anſ
    0.99
    Activations Density 0.129%

    No Known Activations