© 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-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8909
    Prev
    Next
    INDEX
    Explanations

    phrases related to offering assistance or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 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
     bandeira
    -0.42
     sequência
    -0.35
     frigor
    -0.34
     conozco
    -0.34
     coroa
    -0.33
     zonne
    -0.32
     montanha
    -0.32
     ää
    -0.31
     cadeira
    -0.31
     nyky
    -0.30
    POSITIVE LOGITS
    help
    1.70
    Help
    1.66
     Help
    1.64
     help
    1.63
    helps
    1.57
    helped
    1.57
    helping
    1.56
     Helps
    1.54
     helps
    1.49
     Helped
    1.48
    Activations Density 0.101%

    No Known Activations