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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 14661
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to clinical trial methodology and participant management

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

    Randomized controlled trials and placebo treatments

    np_acts-logits-general · gemini-2.0-flash

    randomization or placebo allocation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ustomed
    -0.43
    hella
    -0.42
    lelő
    -0.42
     ne
    -0.39
    持つ
    -0.38
    ljiv
    -0.38
     <<
    -0.38
    typeparam
    -0.38
    edon
    -0.38
    ciso
    -0.38
    POSITIVE LOGITS
     randomization
    1.08
     placebo
    1.01
     Placebo
    0.93
     randomized
    0.89
    Treatments
    0.87
     randomised
    0.87
    treatment
    0.86
     Treatments
    0.84
     Efq
    0.84
    Treatment
    0.82
    Activations Density 1.980%

    No Known Activations