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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8487
    Prev
    Next
    INDEX
    Explanations

    instances of the word "wait" and its variations, indicating themes of anticipation or delay

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ://$
    -0.49
    CrossRef
    -0.40
     soul
    -0.37
     Großen
    -0.37
     Gemeinsame
    -0.36
     Cien
    -0.35
     deep
    -0.35
     ChromeDriver
    -0.35
     destructive
    -0.35
     extremely
    -0.35
    POSITIVE LOGITS
     wait
    1.43
    wait
    1.38
     waiting
    1.36
     Waiting
    1.35
     waits
    1.34
     Wait
    1.32
    Wait
    1.29
    Waiting
    1.27
    waiting
    1.27
     WAIT
    1.23
    Activations Density 0.050%

    No Known Activations