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-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11295
    Prev
    Next
    INDEX
    Explanations

    important results or figures in a document, particularly those highlighted or formatted in bold or italics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.40
    ="@+
    -0.35
    انتهای
    -0.35
    awtextra
    -0.35
     endblock
    -0.34
    djangoproject
    -0.34
     lienzo
    -0.34
    CreateModel
    -0.34
    MemoryWarning
    -0.32
    migrationBuilder
    -0.31
    POSITIVE LOGITS
     highlighted
    1.80
     underlined
    1.67
     highlight
    1.63
     highlighting
    1.52
     Highlight
    1.50
     highlights
    1.48
    highlighted
    1.45
     underline
    1.42
    highlight
    1.41
    Highlight
    1.37
    Activations Density 0.738%

    No Known Activations