© 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. 5783
    Prev
    Next
    INDEX
    Explanations

    phrases related to freedom and release from captivity or constraints

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

    setting someone/something free

    np_acts-logits-general · gemini-2.0-flash

    set free or released

    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
    Hentet
    -0.59
    庁
    -0.54
    esteld
    -0.52
    tvguidetime
    -0.50
    PreferredItem
    -0.48
     facie
    -0.46
    XmlRootElement
    -0.43
    addTab
    -0.43
    Referanser
    -0.42
    sunter
    -0.41
    POSITIVE LOGITS
     release
    2.22
     released
    2.03
     freeing
    2.03
     Release
    1.99
     freed
    1.98
    release
    1.95
    Release
    1.88
     releases
    1.88
     releasing
    1.86
     RELEASE
    1.84
    Activations Density 0.305%

    No Known Activations