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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 15697
    Prev
    Next
    INDEX
    Explanations

    references to news sources and their articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     borboleta
    -0.38
     Soviet
    -0.36
     Suomessa
    -0.35
     skú
    -0.35
    Soorten
    -0.35
     Table
    -0.34
    larımız
    -0.34
     manuales
    -0.33
     ejemplares
    -0.33
     pilota
    -0.33
    POSITIVE LOGITS
     news
    1.15
    news
    0.93
     News
    0.86
     notícia
    0.84
     NEWS
    0.83
    News
    0.81
     headlines
    0.81
    NEWS
    0.80
     noticias
    0.80
     Newsroom
    0.79
    Activations Density 0.290%

    No Known Activations