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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 24327
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to complex mathematical computations and classes

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

    complex numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.51
    principalTable
    -0.50
     noDo
    -0.49
    #![
    -0.46
    Datuak
    -0.45
     jScrollPane
    -0.42
    DeleteBehavior
    -0.42
     [''],
    -0.40
     <=",
    -0.40
    aarrggbb
    -0.40
    POSITIVE LOGITS
     complex
    1.04
    Complex
    1.02
    complex
    1.00
     Complex
    0.99
    COMPLEX
    0.89
     compleja
    0.87
     complejos
    0.87
     COMPLEX
    0.84
     komplex
    0.81
     complexe
    0.80
    Activations Density 0.197%

    No Known Activations