© 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. 3645
    Prev
    Next
    INDEX
    Explanations

    phrases related to measurements or characteristics of products and experiences

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

    Following personal opinions and experiences

    np_acts-logits-general · gemini-2.0-flash

    non-standard words

    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
     ―――――
    -1.12
    ​—
    -1.11
     itſelf
    -1.11
     iſt
    -1.08
     uſ
    -1.07
     fufficient
    -1.04
     ſy
    -1.02
     ſind
    -1.02
     ſtate
    -1.01
     ſeveral
    -1.01
    POSITIVE LOGITS
     alot
    1.20
     coté
    1.05
     loosing
    1.00
     didalam
    0.98
     diatas
    0.96
    慢慢的
    0.91
    .....
    0.91
     میتوان
    0.90
     thier
    0.89
     thats
    0.89
    Activations Density 6.154%

    No Known Activations