© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 6813
    Prev
    Next
    INDEX
    Explanations

    references to collaboration and shared experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ClientRect
    -0.57
    今度は
    -0.50
    forName
    -0.49
     الحره
    -0.48
     ModelExpression
    -0.48
     configureStore
    -0.47
    ChildScrollView
    -0.45
     viewType
    -0.44
    といって
    -0.44
    errHandler
    -0.44
    POSITIVE LOGITS
     sowie
    2.23
     ainsi
    2.02
    以及
    2.00
     serta
    1.95
     nonché
    1.92
     oraz
    1.88
     valamint
    1.88
     aswell
    1.86
     plus
    1.83
     sekä
    1.80
    Activations Density 1.597%

    No Known Activations