© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6467
    Prev
    Next
    INDEX
    Explanations

    Java keywords and constructs, especially those related to asynchronous programming and method definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .*")]
    -0.48
    Transkript
    -0.47
    layoutControl
    -0.45
     again
    -0.44
    esModule
    -0.39
    ChromeDriver
    -0.38
    บ้าง
    -0.37
     lagi
    -0.37
     pungkas
    -0.36
    ❉
    -0.36
    POSITIVE LOGITS
     चीज़ों
    0.60
    featureID
    0.57
    oa̍t
    0.53
    webElementXpaths
    0.53
    BufferException
    0.49
    뀝
    0.48
     ब्रेकडाउन
    0.48
    phère
    0.48
    saraba
    0.48
     Ums
    0.45
    Activations Density 0.873%

    No Known Activations