© 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. 18-GEMMASCOPE-RES-16K
    6. 11302
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic impact and job creation

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

    "economy" after articles

    np_acts-logits-general · gemini-2.0-flash

    economy and inflation

    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
    AttributeSet
    -0.64
    klub
    -0.54
    esseurs
    -0.49
    styleUrls
    -0.48
     Pública
    -0.48
     cref
    -0.48
     parfa
    -0.47
     שוליים
    -0.47
     Municipalidad
    -0.47
    ugc
    -0.47
    POSITIVE LOGITS
     economy
    2.53
     economic
    2.27
    economy
    2.05
     Economy
    2.04
    economic
    1.91
    Economy
    1.90
     Economic
    1.88
    Economic
    1.82
     economies
    1.80
     ECONOMY
    1.80
    Activations Density 0.149%

    No Known Activations