Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 2629
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    |}{\
    -0.47
     falt
    -0.46
    roupa
    -0.44
     cao
    -0.44
     Мексичка
    -0.43
     Kele
    -0.43
    ButterKnife
    -0.42
    vensk
    -0.42
     kele
    -0.41
     gre
    -0.41
    POSITIVE LOGITS
     AssemblyCulture
    0.92
     disambiguazione
    0.88
    principalTable
    0.78
     EconPapers
    0.77
     intStringLen
    0.72
    UnusedPrivate
    0.72
    ьаж
    0.71
    AndEndTag
    0.71
    TintMode
    0.71
    Hentet
    0.70
    Activations Density 0.520%

    No Known Activations