© 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. 15332
    Prev
    Next
    INDEX
    Explanations

    information about people's identities and roles, particularly their professional backgrounds and affiliations

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

    Follows "is" or "was" describing a person

    np_acts-logits-general · gemini-2.0-flash

    is/was followed by past participle

    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
     فريبيس
    -0.86
    Demografie
    -0.72
    WriteTagHelper
    -0.64
    MLLoader
    -0.63
    verwijspagina
    -0.62
    RefNanny
    -0.61
    原始内容存档于
    -0.61
    oulli
    -0.60
    IndentedString
    -0.58
    الحياه
    -0.58
    POSITIVE LOGITS
     a
    0.86
     an
    0.72
     one
    0.70
     part
    0.69
     known
    0.67
     the
    0.65
     employed
    0.65
     president
    0.63
    CloseOperation
    0.62
     married
    0.61
    Activations Density 0.324%

    No Known Activations