Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1915
    Prev
    Next
    INDEX
    Explanations

    key phrases related to customer service issues and complaints

    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
    EnableWeb
    -0.57
    colgroup
    -0.55
    finally
    -0.55
    왠
    -0.54
    ộm
    -0.52
    Whew
    -0.52
    StatusCodes
    -0.51
    ientôt
    -0.51
    temon
    -0.51
     Version
    -0.51
    POSITIVE LOGITS
    setViewportView
    0.75
     argumento
    0.72
     argument
    0.71
    又不是
    0.69
     disagree
    0.68
    あなたが
    0.67
    FTFY
    0.63
     your
    0.62
    Referències
    0.62
     Irrelevant
    0.61
    Activations Density 0.729%

    No Known Activations