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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 11122
    Prev
    Next
    INDEX
    Explanations

    words and phrases specifically related to news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reverso
    -0.86
     ModelExpression
    -0.77
    AndEndTag
    -0.76
    IContainer
    -0.74
     Hepburn
    -0.73
     Archipelago
    -0.71
    ostok
    -0.71
    HasAnnotation
    -0.71
    ="">
    
    -0.69
     Stiftung
    -0.69
    POSITIVE LOGITS
     NEWS
    1.56
     news
    1.51
     News
    1.38
    news
    1.37
    News
    1.33
    NEWS
    1.28
     Newsom
    1.02
     Nachrichten
    0.91
     tidings
    0.85
     noticia
    0.84
    Activations Density 0.046%

    No Known Activations