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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8414
    Prev
    Next
    INDEX
    Explanations

    references to the Django web framework and its components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gefü
    -0.32
     produisons
    -0.29
     τέ
    -0.29
     सुन
    -0.29
     Bestimm
    -0.28
     Matheson
    -0.28
    subplots
    -0.27
    autorité
    -0.27
    AfterViewInit
    -0.27
     prepared
    -0.27
    POSITIVE LOGITS
     django
    2.38
    django
    1.57
     Django
    1.30
    DJANGO
    1.25
    Django
    1.20
    TypedDataSet
    0.90
    djangoproject
    0.89
     queſta
    0.79
    BASEPATH
    0.76
    jango
    0.75
    Activations Density 0.022%

    No Known Activations