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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3656
    Prev
    Next
    INDEX
    Explanations

    references to task forces and their actions

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

    followed by "task" or "tasks"

    np_acts-logits-general · gemini-2.0-flash

    task force

    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
    expression
    -0.65
    Eksteraj
    -0.59
    swe
    -0.59
    いる
    -0.57
     Expression
    -0.57
    ︎
    -0.57
    expressions
    -0.56
     sparing
    -0.54
     facial
    -0.54
    tlement
    -0.54
    POSITIVE LOGITS
     tasks
    1.41
    tasks
    1.31
     Tasks
    1.31
     task
    1.25
     Task
    1.20
    Tasks
    1.19
     TASK
    1.18
    getTask
    1.11
    addTask
    1.10
    TASK
    1.09
    Activations Density 0.043%

    No Known Activations