Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3157
    Prev
    Next
    INDEX
    Explanations

    discussions about waiting and anticipation

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

    waiting or delaying

    np_acts-logits-general · gemini-2.0-flash

    waiting

    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
    erdings
    -0.51
     насељу
    -0.47
    Personendaten
    -0.45
     trách
    -0.43
     PyTuple
    -0.41
     succeeds
    -0.41
    Vind
    -0.40
    entials
    -0.39
     collapsing
    -0.39
     Plu
    -0.39
    POSITIVE LOGITS
     waiting
    3.52
     wait
    3.45
     waited
    3.18
     waits
    3.10
     Waiting
    3.10
     Wait
    2.88
    waiting
    2.88
    Waiting
    2.86
    wait
    2.84
    Wait
    2.75
    Activations Density 0.440%

    No Known Activations