© 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. 15069
    Prev
    Next
    INDEX
    Explanations

    concepts related to mental health conditions and their treatment

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

    "On one hand" or enumerations

    np_acts-logits-general · gemini-2.0-flash

    on the one hand

    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
    migrationBuilder
    -0.55
     للمعارف
    -0.45
    Lähteet
    -0.43
     CoreData
    -0.41
     fubject
    -0.40
     nakalista
    -0.40
     myſelf
    -0.39
    uksessa
    -0.39
     DMG
    -0.38
     ↑
    -0.37
    POSITIVE LOGITS
     one
    1.25
    Firstly
    1.06
     Firstly
    1.06
     starters
    0.97
     firstly
    0.95
     einerseits
    0.88
     transférez
    0.82
     jednej
    0.77
    一个是
    0.77
    一是
    0.77
    Activations Density 0.186%

    No Known Activations