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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 360
    Prev
    Next
    INDEX
    Explanations

    elements related to research parameters and methodologies in clinical studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.85
    ########.
    -0.81
     AssemblyTitle
    -0.80
    djangoproject
    -0.76
     OFDb
    -0.76
     /\.(
    -0.74
     незавершена
    -0.74
    Rüyada
    -0.73
     ruining
    -0.73
     BigInt
    -0.71
    POSITIVE LOGITS
     identified
    0.61
     provide
    0.59
     development
    0.57
     core
    0.55
     process
    0.55
     prior
    0.54
     focus
    0.53
     conceptual
    0.53
     significantly
    0.52
     support
    0.51
    Activations Density 0.647%

    No Known Activations