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

    Neuronpedia

    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. 25-GEMMASCOPE-RES-16K
    6. 2241
    Prev
    Next
    INDEX
    Explanations

    terms related to automotive industry recognition and awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stuff
    -0.97
     probably
    -0.97
     supposedly
    -0.96
    Basically
    -0.94
     Apparently
    -0.92
     Basically
    -0.92
     Probably
    -0.91
     basically
    -0.90
     thingy
    -0.89
     maybe
    -0.88
    POSITIVE LOGITS
     
    0.83
    ®,
    0.82
    . 
    0.77
    ™,
    0.74
    ®
    0.73
    ®.
    0.70
    ℠
    0.68
     impactful
    0.65
     leveraging
    0.64
     featuring
    0.64
    Activations Density 0.402%

    No Known Activations