© 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. 43088
    Prev
    Next
    INDEX
    Explanations

    references to the Gson library and its functionalities related to JSON processing

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

    JSON deserialization

    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
    endphp
    -0.50
    hObject
    -0.36
    __":
    -0.33
    Lihat
    -0.32
     ever
    -0.32
     '{@
    -0.30
    就算
    -0.29
    ruptedException
    -0.28
     بلد
    -0.28
     figures
    -0.28
    POSITIVE LOGITS
     Gson
    1.45
     OkHttpClient
    1.34
     ObjectMapper
    1.24
     InputDecoration
    0.93
    mbggenerated
    0.76
     Administrativna
    0.74
     Alamofire
    0.71
     ویکی‌پدیا
    0.69
    ofType
    0.68
    MLLoader
    0.65
    Activations Density 0.001%

    No Known Activations