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. 14-GEMMASCOPE-RES-16K
    6. 12828
    Prev
    Next
    INDEX
    Explanations

    keywords related to data processing and analysis using Spark in a software context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seamnă
    -0.75
     esternos
    -0.72
     nahilalakip
    -0.71
     propOrder
    -0.69
    ContentLoaded
    -0.69
    Personendaten
    -0.69
    EndGlobalSection
    -0.68
    OfWork
    -0.67
    Diwedd
    -0.67
     grève
    -0.67
    POSITIVE LOGITS
    μβρίου
    0.49
    rzost
    0.46
     useState
    0.43
     system
    0.42
    borderSide
    0.42
    oghi
    0.41
     noDo
    0.41
     *
    0.38
    msup
    0.38
    AddHtmlAttribute
    0.38
    Activations Density 1.789%

    No Known Activations