© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 3354
    Prev
    Next
    INDEX
    Explanations

    terms related to financial or legal obligations and expenses

    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
    ieteur
    -0.72
    ]]
    
    -0.71
     ivelany
    -0.70
    )')
    -0.70
    >')
    -0.69
    ]**
    -0.67
    msgTypes
    -0.66
     recientes
    -0.65
    $'
    -0.65
    esModule
    -0.64
    POSITIVE LOGITS
     with
    0.61
     from
    0.56
     to
    0.54
     in
    0.54
     through
    0.52
     for
    0.51
     against
    0.49
     here
    0.48
     on
    0.47
     swoim
    0.45
    Activations Density 0.889%

    No Known Activations