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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 5468
    Prev
    Next
    INDEX
    Explanations

    instructions or steps related to web-based tasks

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

    GUI elements: links, buttons, icons

    np_acts-logits-general · gemini-2.0-flash

    clicking UI elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.74
     通販
    -0.62
     OMIT
    -0.61
     AssemblyTitle
    -0.60
     propOrder
    -0.56
    TableModel
    -0.56
     beginnetje
    -0.55
    ynb
    -0.52
     protoimpl
    -0.51
    xmlhttp
    -0.50
    POSITIVE LOGITS
     anywhere
    0.62
    anywhere
    0.53
    Initializable
    0.53
     onOptions
    0.52
     Dreyfus
    0.52
    ramentas
    0.52
    ramenta
    0.52
    톱
    0.51
     Anywhere
    0.50
     toolbar
    0.50
    Activations Density 0.190%

    No Known Activations