© 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-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 27891
    Prev
    Next
    INDEX
    Explanations

    references to Android-related programming components or libraries

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

    graphics and display metrics

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    曖昧さ回避
    -1.15
    matchCondition
    -1.02
     "..\..\
    -1.00
     "..\..\..\
    -0.99
     propOrder
    -0.97
    WireFormatLite
    -0.90
     otomatig
    -0.84
    exitRule
    -0.82
    InjectAttribute
    -0.82
    참고
    -0.78
    POSITIVE LOGITS
    Clik
    2.41
     ancla
    0.52
    timb
    0.51
    JpaRepository
    0.49
    ENDIAN
    0.49
     Cib
    0.47
    FileManager
    0.46
    IGraphics
    0.44
    URBANA
    0.44
    DebuggerStep
    0.43
    Activations Density 0.002%

    No Known Activations