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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-GEMMASCOPE-RES-16K
    6. 5919
    Prev
    Next
    INDEX
    Explanations

    instances of the word "complete" and its variations, indicating a focus on completion or tasks being finished

    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
     mux
    -0.73
    zzard
    -0.65
    Nicky
    -0.64
    SAY
    -0.63
    spyOn
    -0.63
     vermelhas
    -0.61
    fontsize
    -0.61
     SAY
    -0.60
    onomie
    -0.60
     Txt
    -0.59
    POSITIVE LOGITS
     completed
    1.71
    completed
    1.58
     completion
    1.53
     comple
    1.50
     completing
    1.50
     Comple
    1.49
     completes
    1.48
     Completing
    1.44
     Completed
    1.42
    Completed
    1.40
    Activations Density 0.061%

    No Known Activations