© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1331
    Prev
    Next
    INDEX
    Explanations

    terms related to tenant and landlord relationships

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

    terms related to agricultural workers and tenancy arrangements

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

    tenant and tenancy

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    setVerticalGroup
    -0.67
    thâu
    -0.66
     transfieras
    -0.66
    isexual
    -0.64
    oluted
    -0.63
     arşivlendi
    -0.62
    IUrlHelper
    -0.61
    subsubsection
    -0.59
     snippetHide
    -0.59
    usakan
    -0.58
    POSITIVE LOGITS
     tenants
    0.82
     незавершена
    0.81
     Tenants
    0.71
     tenant
    0.55
     tensorflow
    0.54
    zwei
    0.54
    laires
    0.53
    DIPSETTING
    0.53
     Renaud
    0.53
     psycopg
    0.52
    Activations Density 0.007%

    No Known Activations