© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9813
    Prev
    Next
    INDEX
    Explanations

    calls for more information or details about a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "More" followed by "information"

    np_acts-logits-general · gemini-2.0-flash

    more information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     demais
    -0.60
    UseVisualStyle
    -0.52
     gawas
    -0.52
     WebDriverWait
    -0.51
    MigrationBuilder
    -0.51
    openConnection
    -0.51
     autrement
    -0.50
     totalSupply
    -0.50
    __()
    -0.48
     supérieurs
    -0.48
    POSITIVE LOGITS
     information
    0.82
     info
    0.69
    fromnode
    0.68
    information
    0.66
     tales
    0.59
     Information
    0.59
     details
    0.58
    Sucesor
    0.58
     INFORMATION
    0.57
    Information
    0.56
    Activations Density 0.092%

    No Known Activations