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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5078
    Prev
    Next
    INDEX
    Explanations

    the structural elements of an HTML document

    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
    LEncoder
    -0.62
    ="@+
    -0.62
     <>",
    -0.61
     transfieras
    -0.57
     незавершена
    -0.53
    protoimpl
    -0.52
    blurRadius
    -0.52
    ftagPool
    -0.51
     iprot
    -0.50
     Autorizaciones
    -0.49
    POSITIVE LOGITS
    centralwidget
    0.64
    body
    0.63
    setContentView
    0.54
     doInBackground
    0.52
    Body
    0.50
    ViewFeatures
    0.49
     body
    0.47
    enterOuterAlt
    0.46
     BODY
    0.45
     initComponents
    0.44
    Activations Density 0.026%

    No Known Activations