© 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. 6134
    Prev
    Next
    INDEX
    Explanations

    variations of the term "strain" in relation to measurement and analysis in materials science

    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
     kaarangay
    -0.49
    didSet
    -0.46
    riculum
    -0.43
    ภัณฑ์
    -0.43
    initializeApp
    -0.43
     nahilalakip
    -0.42
    __*/
    -0.41
    nologue
    -0.40
    UpdatedBy
    -0.40
    genes
    -0.39
    POSITIVE LOGITS
    tainer
    0.50
     AIN
    0.47
    est
    0.47
    ers
    0.46
    ain
    0.45
    ObjectContext
    0.45
    
    0.45
    Ain
    0.43
    AxisAlignment
    0.43
    age
    0.42
    Activations Density 0.546%

    No Known Activations