Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 7425
    Prev
    Next
    INDEX
    Explanations

    references to electronic devices and their specifications

    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
     terpisah
    -0.38
     coches
    -0.38
    einander
    -0.38
     kendaraan
    -0.38
     Bäume
    -0.37
     mikina
    -0.36
     Wikiseite
    -0.36
     isolada
    -0.36
     voitures
    -0.35
     isolado
    -0.35
    POSITIVE LOGITS
     processor
    1.13
     processors
    1.00
     Processor
    0.98
     hardware
    0.94
     Processors
    0.90
     CPU
    0.89
     chipset
    0.85
     wifi
    0.84
     procesador
    0.84
     HDMI
    0.84
    Activations Density 0.488%

    No Known Activations