© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15435
    Prev
    Next
    INDEX
    Explanations

    terms related to ownership and possession

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

    ownership

    np_acts-logits-general · gemini-2.0-flash

    ownership and owners

    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
     nahilalakip
    -1.08
     дописавши
    -0.97
    tagHelperRunner
    -0.94
    NameInMap
    -0.91
     سكانية
    -0.86
    matchCondition
    -0.85
    MigrationBuilder
    -0.82
    GEBURTSDATUM
    -0.81
    setVerticalGroup
    -0.81
    __':
    -0.80
    POSITIVE LOGITS
    hips
    0.78
     owners
    0.70
    owners
    0.66
    ership
    0.66
    Owners
    0.64
     Owners
    0.62
    hip
    0.60
    OWNER
    0.56
     OWNER
    0.54
    esk
    0.53
    Activations Density 0.098%

    No Known Activations