© 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. 10775
    Prev
    Next
    INDEX
    Explanations

    instances where actions or changes are being made in response to situations

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

    Beginning of a sentence, often after a conjunction

    np_acts-logits-general · gemini-2.0-flash

    therefore followed by verb

    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
    ſelf
    -0.87
     Monfieur
    -0.86
     itſelf
    -0.85
     poffe
    -0.84
     houſe
    -0.84
     Diſ
    -0.83
     Theſe
    -0.83
    ſelves
    -0.82
     Eſ
    -0.81
     ſtate
    -0.80
    POSITIVE LOGITS
     decided
    1.03
    于是
    0.80
     began
    0.79
     daarom
    0.75
    於是
    0.74
    decided
    0.73
     derfor
    0.72
     décide
    0.72
    จึง
    0.72
     opted
    0.71
    Activations Density 0.419%

    No Known Activations