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. 18-GEMMASCOPE-RES-16K
    6. 8495
    Prev
    Next
    INDEX
    Explanations

    phrases indicating waiting for someone or something

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

    "waiting" or its variations

    np_acts-logits-general · gemini-2.0-flash

    waiting for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "/",
    -0.46
    ciuta
    -0.45
    cinha
    -0.44
    yesi
    -0.42
    ==",
    -0.41
    viesa
    -0.41
    cinhas
    -0.41
    ulsión
    -0.41
     seien
    -0.40
    ewear
    -0.40
    POSITIVE LOGITS
     waiting
    3.25
     Waiting
    2.81
     awaiting
    2.73
     await
    2.71
    waiting
    2.65
    Waiting
    2.58
     awaits
    2.55
     waits
    2.47
     wait
    2.46
     waited
    2.36
    Activations Density 0.256%

    No Known Activations