© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 13353
    Prev
    Next
    INDEX
    Explanations

    technical specifications and performance details related to mechanical parts, particularly in vehicles and tools

    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
     stos
    -0.32
     Hochsch
    -0.30
     extremely
    -0.24
     e
    -0.23
     söyledi
    -0.23
     chiesa
    -0.22
     доволь
    -0.22
    nskap
    -0.22
     bestaan
    -0.22
    च्या
    -0.22
    POSITIVE LOGITS
     durability
    1.09
     portability
    0.98
     ergonomics
    0.97
     stability
    0.95
     rigidity
    0.93
     flexibility
    0.93
     functionality
    0.92
     airflow
    0.91
     scalability
    0.91
     versatility
    0.89
    Activations Density 0.681%

    No Known Activations