© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 58750
    Prev
    Next
    INDEX
    Explanations

    instances of programming concepts, particularly related to macros and syntactic structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    syntactic sugar or denotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.57
    ImageContext
    -0.52
    GraphicsUnit
    -0.50
     MessageBoxIcon
    -0.49
     mijne
    -0.47
     MaterialApp
    -0.47
     zijne
    -0.47
     fær
    -0.46
    styleUrls
    -0.45
     pinulongan
    -0.45
    POSITIVE LOGITS
    MessageOf
    0.47
     soigne
    0.40
     насељу
    0.38
    الدراسه
    0.36
    toHaveBeen
    0.36
     CallOverrides
    0.36
    baomidou
    0.35
     similarly
    0.35
    Jereo
    0.33
    SuppressMessage
    0.33
    Activations Density 0.552%

    No Known Activations