© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7506
    Prev
    Next
    INDEX
    Explanations

    terms related to demonstration or showing evidence

    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
     Normdatei
    -0.91
    ########.
    -0.85
     Cardona
    -0.80
    حياته
    -0.77
     Kingfisher
    -0.75
    NewUrlParser
    -0.75
    bootstrapcdn
    -0.74
     regards
    -0.72
     AssemblyCulture
    -0.71
    حياتها
    -0.71
    POSITIVE LOGITS
     demonstrations
    1.52
     demonstrators
    1.51
     demos
    1.50
     demonstration
    1.50
     Demonstration
    1.46
    Demonstration
    1.40
     Demo
    1.39
     demo
    1.38
     Demonstr
    1.37
     Demos
    1.35
    Activations Density 0.094%

    No Known Activations