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

    Neuronpedia

    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. 1857
    Prev
    Next
    INDEX
    Explanations

    phrases and aspects related to health and disease

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

    preceding superlatives

    np_acts-logits-general · gemini-2.0-flash

    most, greatest, highest

    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
     alternative
    -0.49
    XmlAccessType
    -0.47
    InlineData
    -0.46
    __":
    -0.44
    AlterField
    -0.44
    __':
    -0.43
    kind
    -0.43
    spyOn
    -0.43
    ValueStyle
    -0.42
    というのも
    -0.42
    POSITIVE LOGITS
     most
    2.01
     greatest
    1.83
     largest
    1.74
     hardest
    1.72
     loudest
    1.72
    greatest
    1.71
     longest
    1.69
    most
    1.69
     strongest
    1.67
     가장
    1.66
    Activations Density 0.639%

    No Known Activations