© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15799
    Prev
    Next
    INDEX
    Explanations

    terms related to assessments of population dynamics and environmental factors

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

    before a list of items

    np_acts-logits-general · gemini-2.0-flash

    technical and abstract nouns

    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
     and
    -0.82
     &
    -0.69
     or
    -0.60
    性和
    -0.58
    اریخ
    -0.57
     surla
    -0.54
     &&
    -0.54
     Utilizamos
    -0.54
     πρά
    -0.51
    Erfolge
    -0.51
    POSITIVE LOGITS
     alike
    1.19
    TargetException
    0.98
     sowie
    0.90
     cherchés
    0.80
     दोनों
    0.79
    sowie
    0.73
    StructEnd
    0.72
     سكانية
    0.70
     שוליים
    0.69
     serta
    0.69
    Activations Density 1.006%

    No Known Activations