© 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. 38-GEMMASCOPE-RES-16K
    11. 9841
    Prev
    Next
    INDEX
    Explanations

    references to customer support interactions and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    customer service complaints and negative interactions with companies or support representatives.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     natin
    -0.50
    Portail
    -0.49
    ulex
    -0.48
    Audiences
    -0.46
     juries
    -0.45
     تضيفلها
    -0.45
     vaak
    -0.44
     audiences
    -0.44
    XtraBars
    -0.44
    ⓧ
    -0.44
    POSITIVE LOGITS
     supuestamente
    0.76
     supposedly
    0.68
     told
    0.66
     rudely
    0.66
     apologized
    0.66
     promised
    0.65
     refunded
    0.62
     emailed
    0.61
     Apparently
    0.59
     apparently
    0.58
    Activations Density 0.437%

    No Known Activations