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. 20-GEMMASCOPE-RES-16K
    6. 12277
    Prev
    Next
    INDEX
    Explanations

    phrases expressing hope and helpfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following an expression of hope or conclusion

    np_acts-logits-general · gemini-2.0-flash

    hope and helpful phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     later
    -0.62
     successivo
    -0.50
     subsequently
    -0.48
    later
    -0.46
     позже
    -0.44
     hereinafter
    -0.43
     afterwards
    -0.43
    ))[
    -0.43
     Subsequently
    -0.43
    Later
    -0.42
    POSITIVE LOGITS
    以上就是
    1.04
    Hopefully
    0.97
    いかがでしたか
    0.96
     Hopefully
    0.94
    évaluateur
    0.93
     hopefully
    0.91
    hopefully
    0.90
    いかが
    0.90
    Demikian
    0.88
    以上です
    0.87
    Activations Density 0.217%

    No Known Activations