© 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. 4280
    Prev
    Next
    INDEX
    Explanations

    instructions related to settings and configurations

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

    Navigating to settings or configuration options

    np_acts-logits-general · gemini-2.0-flash

    navigating to settings

    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
    UnusedPrivate
    -0.77
    BeginContext
    -0.72
    IntoConstraints
    -0.71
    invokeLater
    -0.71
     مرئيه
    -0.70
    awaiter
    -0.70
    isContained
    -0.67
    expandindo
    -0.64
     BIBSYS
    -0.61
     ChromeDriver
    -0.61
    POSITIVE LOGITS
     settings
    1.76
     Settings
    1.65
    Settings
    1.53
    settings
    1.53
     SETTINGS
    1.41
     config
    1.26
     Setting
    1.25
     setting
    1.24
     configuration
    1.22
    SETTINGS
    1.19
    Activations Density 0.475%

    No Known Activations