© 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. 18-GEMMASCOPE-RES-16K
    11. 1768
    Prev
    Next
    INDEX
    Explanations

    phrases related to representation and advocacy on behalf of individuals or organizations

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

    "On [possessive pronoun] behalf"

    np_acts-logits-general · gemini-2.0-flash

    on behalf of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.82
    IntoConstraints
    -0.76
    ImageContext
    -0.73
    MLLoader
    -0.70
     nahilalakip
    -0.67
    LLocation
    -0.65
    makeText
    -0.65
     وتسجيلات
    -0.64
     createContext
    -0.63
    >--}}
    -0.63
    POSITIVE LOGITS
     behalf
    1.88
     mewakili
    1.34
     representing
    1.09
     represent
    1.03
     namens
    0.99
    แทน
    0.96
     represents
    0.95
     représenter
    0.95
     representación
    0.94
     representative
    0.92
    Activations Density 0.322%

    No Known Activations