© 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-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2835
    Prev
    Next
    INDEX
    Explanations

    programming-related elements, particularly code structures and attributes in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.50
    extAlignment
    -0.39
     appelez
    -0.36
     Vol
    -0.35
     Numbers
    -0.35
    Cubit
    -0.34
    iterate
    -0.34
     ri
    -0.34
    Clk
    -0.34
     relâche
    -0.34
    POSITIVE LOGITS
     intStringLen
    0.58
    出版年
    0.56
    HasMaxLength
    0.56
    SharedCtor
    0.55
    RegressionTest
    0.55
     насељу
    0.52
     cromado
    0.51
    exitRule
    0.49
    WebServlet
    0.48
     urbanas
    0.48
    Activations Density 0.300%

    No Known Activations