© 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. 16-GEMMASCOPE-RES-16K
    11. 13249
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions used in formal proofs

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

    Mathematical symbols/notation

    np_acts-logits-general · gemini-2.0-flash

    mathematical inequalities and symbols

    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
    matic
    -0.57
    drawSprites
    -0.55
    Modus
    -0.53
     Automation
    -0.51
     الحره
    -0.50
    (!__
    -0.49
    syn
    -0.49
     Syn
    -0.49
     syn
    -0.48
     Fulda
    -0.47
    POSITIVE LOGITS
    WarningLevel
    0.65
    ViewFeatures
    0.61
     LEYENDO
    0.60
    ConstraintMaker
    0.59
    
    0.59
    rawDesc
    0.57
    ILayout
    0.57
    astify
    0.57
    ChildScrollView
    0.56
     nakalista
    0.56
    Activations Density 3.170%

    No Known Activations