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

    Neuronpedia

    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. 40-GEMMASCOPE-RES-16K
    11. 5665
    Prev
    Next
    INDEX
    Explanations

    phrases related to requests and offers of assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     auroit
    -0.90
     pouvoit
    -0.90
     feroit
    -0.87
     chrétien
    -0.83
     étoit
    -0.82
     vixion
    -0.79
     zijne
    -0.78
     plufieurs
    -0.78
     tijds
    -0.78
     zoude
    -0.78
    POSITIVE LOGITS
     consolidate
    0.70
     introduce
    0.69
     engage
    0.68
     redefine
    0.67
     recreate
    0.67
     prioritize
    0.67
     acquire
    0.66
     establish
    0.66
     reconcile
    0.66
     expand
    0.66
    Activations Density 0.702%

    No Known Activations