© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 148
    Prev
    Next
    INDEX
    Explanations

    phrases related to patient-centered approaches in healthcare

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

    following "a" that describe systems or approaches

    np_acts-logits-general · gemini-2.0-flash

    comprehensive approach or detailed analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.57
    Begriffsklä
    -0.57
     magically
    -0.56
    TestBed
    -0.55
     nakalista
    -0.55
     illegally
    -0.54
     nasty
    -0.54
     ImGui
    -0.54
    tvguidetime
    -0.53
     automaticamente
    -0.52
    POSITIVE LOGITS
     holistic
    1.24
     comprehensive
    1.02
    comprehensive
    0.90
     integrated
    0.89
     integrative
    0.86
     approche
    0.84
     Holistic
    0.84
     approach
    0.81
     multi
    0.80
    approche
    0.79
    Activations Density 0.371%

    No Known Activations