© 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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5294
    Prev
    Next
    INDEX
    Explanations

    concepts of utopias or ideal societies, focusing on social justice and improved futures

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

    preceding "where," "world," or "future."

    np_acts-logits-general · gemini-2.0-flash

    imagined worlds and futures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.55
    baguna
    -0.55
    TableAdapter
    -0.46
     Decke
    -0.45
     transférez
    -0.45
    ftagPool
    -0.45
     madres
    -0.43
     }{@
    -0.43
    Personensuche
    -0.43
     lieben
    -0.42
    POSITIVE LOGITS
     utopia
    0.64
     scenario
    0.62
     world
    0.58
     dystop
    0.57
     utopian
    0.57
     where
    0.56
     vision
    0.54
     envisioned
    0.53
     envision
    0.52
     future
    0.50
    Activations Density 0.471%

    No Known Activations