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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 7230
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to graphics and audio sessions in a coding context

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

    Code related to UI frameworks or audio sessions

    np_acts-logits-general · gemini-2.0-flash

    `SCN`, `UNIT`, `Session`, `Toast`, `CU`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     članak
    -0.56
    ensement
    -0.54
     oprot
    -0.54
    AfterClass
    -0.53
    횟
    -0.51
     himo
    -0.50
    itosan
    -0.49
    IRQn
    -0.49
    SPATH
    -0.48
    parsedMessage
    -0.48
    POSITIVE LOGITS
     @"/
    0.72
     Jefus
    0.67
    WindowConstants
    0.65
    XmlAccessType
    0.61
     Profesional
    0.61
     FetchType
    0.60
    WireFormatLite
    0.60
    FetchType
    0.59
     Efq
    0.57
    GenerationType
    0.56
    Activations Density 0.294%

    No Known Activations