© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8238
    Prev
    Next
    INDEX
    Explanations

    references to completion or execution of tasks and processes

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

    Preceding word is completed or complete

    np_acts-logits-general · gemini-2.0-flash

    state of being completed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.71
    TypedDataSet
    -0.69
    SequentialGroup
    -0.57
     Undeclared
    -0.56
    AnimationsModule
    -0.55
    ngrx
    -0.54
    Subscribe
    -0.51
     Roskov
    -0.47
    хьтан
    -0.47
    abetes
    -0.47
    POSITIVE LOGITS
     completed
    3.12
     completion
    3.08
     finished
    2.89
     finish
    2.76
     completes
    2.74
     completing
    2.72
     Completed
    2.69
     Completion
    2.68
     finishing
    2.65
    completed
    2.60
    Activations Density 0.614%

    No Known Activations