© 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. 14386
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions relevant to equations in geometry and physics

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

    equation components

    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
     للاسماء
    -0.96
    EDEFAULT
    -0.89
    BufferException
    -0.88
     NSCoder
    -0.85
    SharedDtor
    -0.81
    IndentedString
    -0.80
    ValueStyle
    -0.79
    باردا
    -0.76
    rungsseite
    -0.76
    CppMethod
    -0.75
    POSITIVE LOGITS
     arac
    0.30
     prek
    0.29
    高等
    0.27
     housing
    0.27
    proxy
    0.26
    1
    0.24
    ,
    0.24
     link
    0.24
     cross
    0.24
     тор
    0.24
    Activations Density 0.175%

    No Known Activations