© 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. 35-GEMMASCOPE-RES-16K
    11. 6359
    Prev
    Next
    INDEX
    Explanations

    statements indicating uncertainty and conditional outcomes

    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
     Dionys
    -0.56
    fficio
    -0.55
     hObject
    -0.54
    pecabe
    -0.51
    corpions
    -0.51
     endforeach
    -0.50
    ådet
    -0.49
    siers
    -0.48
    jis
    -0.47
    cises
    -0.46
    POSITIVE LOGITS
     did
    0.72
     does
    0.55
    did
    0.54
    Did
    0.45
     Савезне
    0.40
     Did
    0.39
    Salta
    0.38
     hacerlo
    0.38
    そうで
    0.38
    WindowConstants
    0.36
    Activations Density 0.245%

    No Known Activations