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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 5044
    Prev
    Next
    INDEX
    Explanations

    instances of the word "highlight" or variations of it, indicating an emphasis on significant points or features within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.73
     صوتيه
    -0.72
    ClientSize
    -0.66
     Infine
    -0.65
    zzleHttp
    -0.65
     CGSize
    -0.64
     useAuth
    -0.63
     vallée
    -0.63
    BagLayout
    -0.62
     Kieran
    -0.62
    POSITIVE LOGITS
     highlight
    1.36
     Highlight
    1.20
    Highlight
    1.13
     highlights
    1.10
    highlights
    1.06
     Highlights
    1.00
    Highlights
    0.99
    highlight
    0.95
     sight
    0.91
     Sight
    0.90
    Activations Density 0.071%

    No Known Activations