© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 38833
    Prev
    Next
    INDEX
    Explanations

    references to various types of lattices and their characteristics

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

    square lattice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.59
    LookAnd
    -0.57
     intptr
    -0.56
    Vidite
    -0.55
    SwitchCompat
    -0.54
    ьаж
    -0.51
    JAXB
    -0.47
    jspb
    -0.47
     otomatig
    -0.47
    aarrggbb
    -0.47
    POSITIVE LOGITS
     square
    1.04
     Square
    0.95
     SQUARE
    0.94
    Square
    0.92
    SQUARE
    0.88
    square
    0.87
     squares
    0.84
     cuadrado
    0.83
     quadrado
    0.82
     Squares
    0.81
    Activations Density 0.047%

    No Known Activations