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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 69533
    Prev
    Next
    INDEX
    Explanations

    references to diagrams and flowcharts used in organizational and analytical contexts

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ब्रेकडाउन
    -0.69
    AddTagHelper
    -0.55
    GIVEREF
    -0.54
     CURLOPT
    -0.53
    setAccessible
    -0.50
     OSError
    -0.47
    ]")]
    -0.47
    Hozzáférés
    -0.47
    UnusedPrivate
    -0.45
     getItemId
    -0.45
    POSITIVE LOGITS
     diagrams
    0.73
     diagram
    0.67
     Diagrams
    0.64
     Diagram
    0.58
    Diagram
    0.54
     chart
    0.52
     charts
    0.51
    diagram
    0.51
     picture
    0.49
     sketches
    0.49
    Activations Density 0.065%

    No Known Activations