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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6205
    Prev
    Next
    INDEX
    Explanations

    occurrences of news broadcasts and related programming formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.74
     متعلقه
    -0.72
    Diweddarwch
    -0.72
     InputDecoration
    -0.72
    原始内容存档于
    -0.70
    
    -0.69
    Obrázky
    -0.67
     خارجية
    -0.66
     disambiguazione
    -0.66
    دانشنامهٔ
    -0.65
    POSITIVE LOGITS
     news
    0.69
     broadcast
    0.67
     broadcasts
    0.60
     newspapers
    0.59
     simul
    0.57
     broadcasting
    0.54
     television
    0.53
    Television
    0.52
     sati
    0.52
     MSNBC
    0.52
    Activations Density 0.462%

    No Known Activations