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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 4312
    Prev
    Next
    INDEX
    Explanations

    references to flash technology or devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVEREF
    -0.56
     navideños
    -0.46
     Moscú
    -0.45
     nôtre
    -0.44
     kaarangay
    -0.43
     razie
    -0.42
     circonst
    -0.42
    دانشنامهٔ
    -0.42
     policiales
    -0.41
     Exactos
    -0.41
    POSITIVE LOGITS
     flash
    1.09
    flash
    0.97
     Flash
    0.93
    Flash
    0.88
     FLASH
    0.85
     flashes
    0.77
    FLASH
    0.73
     flashed
    0.67
     Partners
    0.62
     partners
    0.62
    Activations Density 0.090%

    No Known Activations