© 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. 3-GEMMASCOPE-RES-16K
    11. 724
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the action of keeping current or updated

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ölkerung
    -0.60
     finnas
    -0.55
     يتيمه
    -0.54
    writeFieldEnd
    -0.52
     BorderRadius
    -0.51
    TAWA
    -0.51
     оригіналу
    -0.51
     محفوظة
    -0.51
    EndInit
    -0.50
    momix
    -0.48
    POSITIVE LOGITS
    ViewImports
    0.76
    tabPage
    0.64
     Lleva
    0.62
    hastly
    0.62
    JoinTable
    0.61
    */].
    0.60
     Stearns
    0.60
     induction
    0.59
     Induction
    0.56
    OpenHelper
    0.55
    Activations Density 0.376%

    No Known Activations