© 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. 8180
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and phrases related to various research studies and methodologies

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

    preceding "tested," "examined," "in," or "under."

    np_acts-logits-general · gemini-2.0-flash

    examining, testing, analyzing

    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
    phyllum
    -0.50
    исленность
    -0.45
    NOC
    -0.43
    droj
    -0.41
    postmedia
    -0.40
    sist
    -0.40
    一声
    -0.40
    uale
    -0.39
     مكت
    -0.38
    ტ
    -0.38
    POSITIVE LOGITS
     studied
    1.67
     investigated
    1.59
     examined
    1.55
     analyzed
    1.41
     analysed
    1.38
    studied
    1.32
     tested
    1.30
     surveyed
    1.27
     reviewed
    1.26
     étudié
    1.24
    Activations Density 1.267%

    No Known Activations