© 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. 13374
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to media and journalism practices

    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
     Architekt
    -0.56
    ativement
    -0.54
    Демографія
    -0.49
    ظمة
    -0.49
    SharedCtor
    -0.48
     funko
    -0.46
    Specification
    -0.45
    attu
    -0.45
    يكب
    -0.44
    Architect
    -0.44
    POSITIVE LOGITS
     journalism
    1.93
     journalists
    1.88
     reporters
    1.80
     journalistic
    1.78
     Journalism
    1.70
     reporter
    1.66
     Journalists
    1.64
     Reporters
    1.64
     journalist
    1.59
     editors
    1.45
    Activations Density 0.560%

    No Known Activations