© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 3908
    Prev
    Next
    INDEX
    Explanations

    references to specific tasks or task forces

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

    "task"

    np_acts-logits-general · gemini-2.0-flash

    phrases like task force

    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
    expression
    -0.79
     face
    -0.78
     faces
    -0.78
     facial
    -0.76
     countenance
    -0.74
     Expression
    -0.71
     expression
    -0.71
     myſelf
    -0.70
    expressions
    -0.70
     Faces
    -0.69
    POSITIVE LOGITS
     tasks
    1.20
     Tasks
    1.16
    tasks
    1.12
     Task
    1.12
    Tasks
    1.09
     task
    1.09
     TASK
    1.08
    getTask
    1.05
    TASK
    0.97
    Task
    0.97
    Activations Density 0.072%

    No Known Activations