© 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. 39-GEMMASCOPE-RES-16K
    11. 3241
    Prev
    Next
    INDEX
    Explanations

    code-like structures and syntax elements 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 @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.49
    AndEndTag
    -0.47
    onymie
    -0.44
    berdayakan
    -0.43
     HasFactory
    -0.42
     Taktlose
    -0.41
     marinho
    -0.41
     ExecuteAsync
    -0.40
    RegressionTest
    -0.40
     esportivo
    -0.40
    POSITIVE LOGITS
     O
    3.03
     o
    2.64
    O
    2.19
     о
    1.80
     ओ
    1.38
     О
    1.34
     ο
    1.34
    o
    1.34
    Ｏ
    1.20
    オ
    1.14
    Activations Density 1.805%

    No Known Activations