© 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. 14816
    Prev
    Next
    INDEX
    Explanations

    terms related to treatment and therapies

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

    medical or data "treatment"

    np_acts-logits-general · gemini-2.0-flash

    treatment effects

    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
     Efq
    -0.84
    GraphicsUnit
    -0.82
    (;;)
    -0.75
    躇
    -0.72
    ReusableCell
    -0.72
     drau
    -0.71
    ohm
    -0.71
    StandardCharsets
    -0.70
    Liefs
    -0.69
    ussis
    -0.69
    POSITIVE LOGITS
     Treat
    1.09
     TREAT
    1.08
    Treat
    1.08
     treat
    1.07
    treat
    1.01
    TREAT
    1.01
     treats
    0.98
    Treating
    0.93
     treating
    0.91
    treated
    0.89
    Activations Density 0.224%

    No Known Activations