© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11880
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculations related to derivatives and factors

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

    "Let" statements in mathematical contexts

    np_acts-logits-general · gemini-2.0-flash

    expressions involving math functions

    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
    Viitteet
    -0.77
    ("")]
    
    -0.68
     مشين
    -0.67
     gynhyrchwyd
    -0.66
    ConstraintMaker
    -0.65
    tagHelperRunner
    -0.64
     Réponses
    -0.64
    PRNewswire
    -0.61
    LayoutConstraint
    -0.60
    Unmarshaller
    -0.60
    POSITIVE LOGITS
     x
    0.63
     
    0.55
    sin
    0.51
     sin
    0.48
    DJANGO
    0.46
     sen
    0.46
    x
    0.44
     ax
    0.44
    ByUrl
    0.44
     tan
    0.43
    Activations Density 3.534%

    No Known Activations