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. 2312
    Prev
    Next
    INDEX
    Explanations

    terms related to contracts and bidding processes

    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
    ValueStyle
    -0.80
    webElementXpaths
    -0.74
     disambiguazione
    -0.67
    BeginInit
    -0.62
    })->
    -0.62
    Handlung
    -0.62
     [*]
    -0.61
    upassen
    -0.60
     Ause
    -0.60
    UrlResolution
    -0.60
    POSITIVE LOGITS
     auprès
    0.57
     involving
    0.53
     for
    0.49
     processed
    0.49
    críbete
    0.48
     tramit
    0.48
     made
    0.45
     zło
    0.44
     process
    0.44
     PROCESS
    0.43
    Activations Density 0.486%

    No Known Activations