© 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. 20-GEMMASCOPE-RES-131K
    11. 116409
    Prev
    Next
    INDEX
    Explanations

    references to the AspectJ programming language

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

    AspectJ programming discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -1.15
     محفوظة
    -0.77
     HttpStatusCode
    -0.70
    sweetalert
    -0.63
     незавершена
    -0.60
    BufferException
    -0.59
     ujednoznacz
    -0.56
    ⓧ
    -0.53
     bağlantılar
    -0.48
    withOpacity
    -0.48
    POSITIVE LOGITS
    ftagPool
    2.36
    ControllerAdvice
    1.53
    setupUi
    1.28
    aspectj
    1.16
    Initializable
    0.97
    Previews
    0.85
    tagPool
    0.79
    Cpp
    0.74
     disambiguazione
    0.65
    WebElementEntity
    0.58
    Activations Density 0.000%

    No Known Activations