© 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. 20-GEMMASCOPE-RES-16K
    11. 9037
    Prev
    Next
    INDEX
    Explanations

    phrases related to parental involvement and the impact of family dynamics on child behavior

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

    Values or statistics being compared

    np_acts-logits-general · gemini-2.0-flash

    versus

    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
    JspWriter
    -0.69
     CreateTagHelper
    -0.66
     Мексичка
    -0.62
     utafitiHapana
    -0.61
     gainera
    -0.59
    )))));
    -0.57
    clusal
    -0.57
    niająca
    -0.56
    hoga
    -0.55
     تضيفلها
    -0.55
    POSITIVE LOGITS
     vs
    4.08
     versus
    3.96
    versus
    3.11
     Vs
    3.10
     Versus
    3.09
    vs
    2.93
     VS
    2.67
    Versus
    2.51
     compared
    2.17
    VS
    2.05
    Activations Density 1.246%

    No Known Activations