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. 1-GEMMASCOPE-RES-16K
    6. 13375
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating permanence or lasting impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -1.03
     myſelf
    -0.99
     ―――――
    -0.95
    Portail
    -0.91
    ſelf
    -0.90
     ainfi
    -0.89
     Anſ
    -0.89
     themſelves
    -0.88
    IsContent
    -0.86
     itſelf
    -0.86
    POSITIVE LOGITS
     arise
    0.88
     forever
    0.81
     loyalty
    0.69
     arises
    0.68
    loyalty
    0.68
     suicide
    0.66
     loyal
    0.65
     jury
    0.65
    forever
    0.64
     Forever
    0.62
    Activations Density 0.083%

    No Known Activations