© 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. 8792
    Prev
    Next
    INDEX
    Explanations

    significant events or statistics related to mortality and economic downturns

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

    Follows the token "this"

    np_acts-logits-general · gemini-2.0-flash

    this decade

    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
     للمعارف
    -0.91
    Rohy
    -0.72
    BeginContext
    -0.71
     oprot
    -0.71
    ніципалі
    -0.68
    TypedDataSet
    -0.66
    protoimpl
    -0.66
     okuyayım
    -0.65
    featureID
    -0.65
     iconTwitter
    -0.61
    POSITIVE LOGITS
    ↵↵↵
    0.54
    Czytaj
    0.44
     recargable
    0.44
    :^{
    0.43
     asiático
    0.42
    НИК
    0.42
     zeg
    0.40
     getLayout
    0.40
     виро
    0.40
    の元
    0.40
    Activations Density 0.105%

    No Known Activations