© 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. 16-GEMMASCOPE-RES-16K
    6. 5367
    Prev
    Next
    INDEX
    Explanations

    first-person narrative perspectives on personal experiences with sewing and fabric crafts

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

    Nostalgia or resurgence

    np_acts-logits-general · gemini-2.0-flash

    revival and resurgence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bný
    -0.54
    ecture
    -0.52
     suivantes
    -0.51
     humaines
    -0.48
    빠
    -0.47
     coucher
    -0.46
    DropColumn
    -0.46
    anganronpa
    -0.46
     religieuses
    -0.45
     culturelles
    -0.44
    POSITIVE LOGITS
     revived
    1.59
     revival
    1.55
     reviving
    1.47
     revive
    1.44
     nostalgia
    1.42
     nostalgic
    1.41
     resurgence
    1.37
     reactiv
    1.32
     revi
    1.31
     Revi
    1.29
    Activations Density 0.537%

    No Known Activations