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. 2152
    Prev
    Next
    INDEX
    Explanations

    phrases related to encouragement and invitations to engage or participate

    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
    帮我
    -0.50
     or
    -0.50
    amanca
    -0.49
     my
    -0.48
    side
    -0.47
     AppComponent
    -0.47
     mir
    -0.46
    ítmény
    -0.46
    /
    -0.45
    contentPane
    -0.45
    POSITIVE LOGITS
     Infórmanos
    0.84
    raszamy
    0.80
     surla
    0.75
     мәкал
    0.74
     تكبرها
    0.73
    Zapraszamy
    0.71
    abestanden
    0.69
    MLLoader
    0.67
    Esperamos
    0.66
    
    0.63
    Activations Density 0.291%

    No Known Activations