© 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. 19-GEMMASCOPE-RES-16K
    6. 2752
    Prev
    Next
    INDEX
    Explanations

    mentions of customer service and support interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.62
    laubnis
    -0.59
     مشين
    -0.57
     noqa
    -0.55
     endforeach
    -0.54
    awtextra
    -0.53
    tableFuture
    -0.53
    Ehrungen
    -0.53
    omitempty
    -0.53
     TextInputType
    -0.52
    POSITIVE LOGITS
     customer
    1.89
     support
    1.78
     Customer
    1.72
    support
    1.63
     Support
    1.63
    Support
    1.62
    Customer
    1.53
    customer
    1.51
     SUPPORT
    1.35
     CUSTOMER
    1.32
    Activations Density 0.172%

    No Known Activations