© 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. 9408
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as function declarations and class constructors

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

    Code and punctuation in code snippets

    np_acts-logits-general · gemini-2.0-flash

    programmer

    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
     itſelf
    -0.78
    UserScript
    -0.76
    ----</
    -0.72
     photolibrary
    -0.72
     transfieras
    -0.71
    StateToProps
    -0.70
    InlineData
    -0.70
    setVerticalGroup
    -0.69
    ſelf
    -0.65
     houſe
    -0.64
    POSITIVE LOGITS
     private
    0.67
     readonly
    0.61
    IBOutlet
    0.60
     var
    0.60
     val
    0.58
    readonly
    0.54
     ostavi
    0.52
     sel
    0.51
     mut
    0.51
    private
    0.51
    Activations Density 0.070%

    No Known Activations