© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 12636
    Prev
    Next
    INDEX
    Explanations

    various types of symbols and notational elements in technical or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.73
     SwitchCompat
    -0.63
    asteel
    -0.61
     שוליים
    -0.59
    enumi
    -0.56
     chrétien
    -0.51
     Parcelable
    -0.51
    ziehungs
    -0.50
    躇
    -0.50
    ública
    -0.49
    POSITIVE LOGITS
    windowFixed
    1.10
    IndentedString
    0.76
     cherchés
    0.70
     disambiguazione
    0.67
     AssemblyCompany
    0.66
    LookAnd
    0.65
    :✨
    0.65
    WriteTagHelper
    0.64
    amoan
    0.63
    Jereo
    0.62
    Activations Density 0.482%

    No Known Activations