© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 6510
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electrical components and their functions

    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
     lifted
    -0.42
     поднима
    -0.39
     подня
    -0.38
     verho
    -0.37
    ificados
    -0.37
    抬起头
    -0.37
    放大
    -0.35
     crecer
    -0.35
     thúc
    -0.35
     elevar
    -0.35
    POSITIVE LOGITS
     decline
    1.99
     declining
    1.82
     decrease
    1.78
     declines
    1.74
     decreasing
    1.73
    decline
    1.70
     Decline
    1.64
    Decline
    1.63
     Decre
    1.62
     decreases
    1.61
    Activations Density 0.824%

    No Known Activations