© 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. 20-GEMMASCOPE-RES-16K
    11. 3918
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting symbols used in programming or markup languages

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

    Code, file paths, or URLs

    np_acts-logits-general · gemini-2.0-flash

    software, legal, and academic texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerPage
    -0.46
    andam
    -0.46
    quel
    -0.45
    ressi
    -0.45
                       
    -0.45
    medaille
    -0.42
                     
    -0.42
         
    -0.42
                            
    -0.41
    rix
    -0.40
    POSITIVE LOGITS
    Personensuche
    1.30
    ReusableCell
    0.89
    دانشنامهٔ
    0.87
    InitVars
    0.86
     nakalista
    0.82
    DebuggerNonUser
    0.80
    ViewFeatures
    0.80
    NameInMap
    0.80
    enterOuterAlt
    0.78
    findpost
    0.77
    Activations Density 0.011%

    No Known Activations