© 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. 2173
    Prev
    Next
    INDEX
    Explanations

    code structure elements, specifically braces and certain programming constructs

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

    Code, namespaces, or URLs containing "org"

    np_acts-logits-general · gemini-2.0-flash

    programming package names

    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
     layui
    -0.62
     rospy
    -0.59
     onAnimation
    -0.56
     LoginComponent
    -0.54
     BitmapFactory
    -0.52
     Taktlose
    -0.52
    PageModule
    -0.52
    loride
    -0.52
    mbic
    -0.51
     tslint
    -0.51
    POSITIVE LOGITS
    MemoryWarning
    0.66
    lamations
    0.59
    }{*}{
    0.58
    UserScript
    0.51
    ortable
    0.51
     Normdatei
    0.51
    ratulations
    0.51
    类型的
    0.50
     types
    0.50
     ớt
    0.50
    Activations Density 0.065%

    No Known Activations