© 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. 35-GEMMASCOPE-RES-16K
    11. 12158
    Prev
    Next
    INDEX
    Explanations

    phrases related to customer service and satisfaction

    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
    */),
    -0.46
    Ideally
    -0.46
    IndentedString
    -0.43
     Ideally
    -0.43
    SharedCtor
    -0.41
    MergeFrom
    -0.40
     ideally
    -0.39
     CanadaChoose
    -0.38
     autorytatywna
    -0.38
    jalá
    -0.36
    POSITIVE LOGITS
     rest
    2.11
    Rest
    1.75
     Rest
    1.72
    rest
    1.64
     REST
    1.27
     rests
    1.26
    REST
    1.20
     reft
    1.19
     rested
    1.17
    rests
    1.11
    Activations Density 0.243%

    No Known Activations