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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7152
    Prev
    Next
    INDEX
    Explanations

    terms related to subscription management and updates

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

    Chinese words for looking, checking, editing

    np_acts-logits-general · gemini-2.0-flash

    find or track shows

    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
     Roskov
    -0.92
    Становништво
    -0.81
    djangoproject
    -0.78
    IContainer
    -0.77
    Demografie
    -0.76
     يتيمه
    -0.75
    esModule
    -0.75
    يكب
    -0.74
    WaitGroup
    -0.74
    렀
    -0.73
    POSITIVE LOGITS
     up
    0.74
    得
    0.63
    着
    0.60
    ed
    0.59
    了
    0.58
    着用
    0.54
    ing
    0.53
     out
    0.52
    得很
    0.51
    up
    0.49
    Activations Density 0.031%

    No Known Activations