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. 8-GEMMASCOPE-RES-16K
    6. 2115
    Prev
    Next
    INDEX
    Explanations

    references to social media and discussions about its impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createSlice
    -0.67
    ArgsConstructor
    -0.62
     tartalomajánló
    -0.62
    тербург
    -0.58
     orquesta
    -0.58
    tagext
    -0.57
    typeorm
    -0.57
     imageNamed
    -0.57
     Orchestra
    -0.56
    ardı
    -0.56
    POSITIVE LOGITS
     internet
    0.90
     Internet
    0.87
     online
    0.83
     web
    0.79
     Twitter
    0.77
    internet
    0.72
     twitter
    0.71
     websites
    0.70
    Internet
    0.69
     Web
    0.68
    Activations Density 0.114%

    No Known Activations