Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 12799
    Prev
    Next
    INDEX
    Explanations

    elements related to news media production and broadcasting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     candles
    -0.43
     cuir
    -0.42
    ativement
    -0.42
     Architekt
    -0.41
    bandcamp
    -0.40
    ظمة
    -0.40
    wicklung
    -0.38
     Architekten
    -0.38
    دکتر
    -0.38
    amazonaws
    -0.38
    POSITIVE LOGITS
     journalism
    2.19
     journalists
    2.13
     journalistic
    2.08
     reporters
    2.01
     Journalism
    1.94
     reporter
    1.90
     Journalists
    1.89
     journalist
    1.88
     Reporters
    1.82
     news
    1.71
    Activations Density 0.580%

    No Known Activations