© 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. 9178
    Prev
    Next
    INDEX
    Explanations

    terms related to acknowledgments and gratitude

    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
     Mussolini
    -0.49
    Huawei
    -0.48
    -£
    -0.48
     "}";
    -0.47
     cantando
    -0.47
     morrer
    -0.46
     sitä
    -0.46
     mourir
    -0.45
    ríguez
    -0.44
    yelidikan
    -0.44
    POSITIVE LOGITS
     Matt
    0.89
     Erin
    0.88
     Beth
    0.83
    Erin
    0.82
     Ryan
    0.79
     Heather
    0.79
    Matt
    0.78
     Amy
    0.78
     Amber
    0.78
     Jen
    0.77
    Activations Density 0.378%

    No Known Activations