Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3531
    Prev
    Next
    INDEX
    Explanations

    annotations related to Java Spring and JPA (Java Persistence API)

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

    Java annotations and testing keywords

    np_acts-logits-general · gemini-2.0-flash

    test annotations

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ########.
    -0.86
     queſta
    -0.79
     يتيمه
    -0.76
     zwiſchen
    -0.74
     betweenstory
    -0.73
     jspb
    -0.72
    niſſe
    -0.71
    bootstrapcdn
    -0.68
     صوتيه
    -0.68
     estekak
    -0.68
    POSITIVE LOGITS
    GetMapping
    0.52
    RequestParam
    0.41
    DataMember
    0.39
    XmlElement
    0.38
    Autowired
    0.37
    PostMapping
    0.36
     épa
    0.35
    ,
    0.35
    ManyToOne
    0.33
    PostConstruct
    0.30
    Activations Density 0.012%

    No Known Activations