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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8594
    Prev
    Next
    INDEX
    Explanations

    percentages and data related to various experiments or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -1.05
    ../../
    -0.99
     censiti
    -0.96
     artefacts
    -0.95
     moulds
    -0.94
     '../../../../
    -0.94
    ]',
    -0.92
    ∆
    -0.91
     Colours
    -0.90
    keycode
    -0.89
    POSITIVE LOGITS
     theaters
    1.13
     disks
    1.11
     gages
    1.09
    și
    1.05
     catalogs
    1.02
     viață
    1.02
     fibers
    1.01
     Theaters
    1.00
    Behaviors
    0.96
    Theater
    0.96
    Activations Density 1.646%

    No Known Activations