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. 12-GEMMASCOPE-RES-16K
    6. 7302
    Prev
    Next
    INDEX
    Explanations

    CSS and style-related properties and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DoubleQuotes
    -0.77
    FormTagHelper
    -0.72
    LookAnd
    -0.65
     дописавши
    -0.61
    Autoritní
    -0.59
    FieldBuilder
    -0.58
     postIndex
    -0.56
    ejb
    -0.56
    contentLoaded
    -0.56
    gelopen
    -0.55
    POSITIVE LOGITS
    fontSize
    0.81
     fontSize
    0.76
    FontOfSize
    0.70
     size
    0.64
    FontSize
    0.64
     fontsize
    0.61
    setFont
    0.60
    small
    0.58
    size
    0.55
    TagMode
    0.53
    Activations Density 0.063%

    No Known Activations