© 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. 7388
    Prev
    Next
    INDEX
    Explanations

    technical terms and key components related to data processing and model management

    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
    createClass
    -0.43
     Liverpool
    -0.41
    Liverpool
    -0.40
     
    -0.40
    stateMutability
    -0.38
    mtable
    -0.38
    ParseTree
    -0.36
    Bitpie
    -0.35
    比特派
    -0.34
     ErrIntOverflow
    -0.34
    POSITIVE LOGITS
     onion
    1.02
    onion
    1.00
     ionic
    0.99
     RON
    0.99
     Leone
    0.98
    alon
    0.95
     Lons
    0.93
     ron
    0.93
     Aron
    0.93
     onions
    0.92
    Activations Density 0.587%

    No Known Activations